Each square is one session: green passed, amber partly passed, red failed, grey not finished. Select a square to replay it.
Agent
T1
T2
T3
T4
T5
T6
Claude Sonnet 5.5
GPT-6.1 Sol
Gemini 4 Argon
DeepSeek V4.1 Flash
T1 I'm setting up a new project and want to know how S3 versioning works. Can you explain what it does and how to turn it on for a bucket?
T2 Which AWS regions are there? I'm trying to see the full list including their codes.
T3 Is Amazon Bedrock available in eu-central-1 and ap-southeast-2? I need to know before I pick where to deploy.
T4 My Lambda function keeps failing with 'Task timed out after 3.00 seconds'. What does that mean and how do I fix it?
T5 What are the current default service quotas for Lambda concurrent executions per region, and can they be raised? Please give me the full details from the docs.
T6 I want to host a static website on AWS cheaply. What are my options, and which one would you suggest for a small personal blog with HTTPS on a custom domain?
aws___search_documentation ranks blogs, FAQs and old SDK pages above canonical how-to pages (S3 versioning)
On T1 (enable S3 versioning), all four agents that searched got blogs, FAQs, CLI/SDK v1 reference pages, Outposts/Lightsail steps or deletion docs. None got the 'Enabling versioning on buckets' how-to page. Every T1 run ended partial. Claude filled the procedure in from memory. Gemini and GPT had no console steps. DeepSeek needed several searches. Results also carry no indication of authority or version, and CLI v1/v2 duplicates crowd out user-guide pages.
Fix: Boost official user-guide how-to and conceptual pages for 'how to enable/configure' queries. Down-rank or filter deprecated SDK v1 reference pages, blogs and FAQs. Deduplicate near-identical CLI v1/v2 results. Add a source-type or doc-version field. Support scoping to a service.
Prompt for your coding agent
In the aws___search_documentation ranking for the AWS Knowledge MCP server, make official user-guide how-to and concept pages (e.g. S3 'Enabling versioning on buckets', Versioning.html) rank above blog posts, FAQs and deprecated SDK v1 reference pages for natural-language 'how do I enable X' queries. Deduplicate near-identical CLI v1/v2 entries and prefer the latest version. Add a source_type and doc_version field to each result. Add an optional service filter. Test with the query 'how to enable versioning on an S3 bucket' and verify the how-to page is in the top 3.
aws___search_documentation snippets are truncated and miss the relevant section (Lambda timeout, quotas, S3 how-to)
Snippets were cut off with '[truncated — additional content omitted]' or returned the wrong section. For T4, results showed 'Verify that your function timed out' instead of the 3-second default and fixes. For T5, the same truncated lambda-concurrency chunk came back repeatedly and the quotas snippet had no table. In T1 the agents could not tell whether the console steps were in the omitted text. In T6 they could not tell whether the HTTPS caveat was covered. Agents needed extra searches or full reads, and T1, T4 and T6 ended partial for several agents.
Fix: Return the chunk most relevant to the query instead of the page start. Clearly mark truncation and give a pointer (URL and offset) to fetch the rest. Avoid returning the same chunk repeatedly across queries.
Prompt for your coding agent
Update aws___search_documentation so each result snippet is the most query-relevant section of the page (e.g. the Lambda 'Timeouts' section or the quota table row) rather than the page start. When a snippet is truncated, include an explicit truncated flag, the page's total length and a character offset or heading so agents can call aws___read_documentation for the rest. Deduplicate identical chunks returned across repeated queries.
aws___search_documentation returns no pricing or CloudFront/ACM content for hosting cost-comparison questions (T6)
On T6 (static site hosting with custom domain, HTTPS and cost), DeepSeek got scattered pricing snippets from marketing FAQs and blogs. It never got Route 53 or S3 storage pricing. Gemini got only Amplify and S3 pages, with no CloudFront/ACM or pricing content. GPT got an older FAQ with outdated per-GB figures instead of the pricing page. DeepSeek returned four near-duplicate Amplify Hosting results that differed only by platform. Claude, DeepSeek and Gemini ended partial.
Fix: Index and rank official pricing pages for the main services. Cover CloudFront and ACM custom-domain docs for hosting queries. Deduplicate platform-variant Amplify pages. Flag when pricing data is missing from the results.
Prompt for your coding agent
Improve aws___search_documentation coverage and ranking for pricing and hosting queries: ensure official pricing pages (Amplify, S3, CloudFront, Route 53) are indexed and returned for 'cost' queries, and that CloudFront and ACM custom-domain/HTTPS docs surface for static-hosting questions. Collapse Amplify results that differ only by platform path (android/flutter/swift/react). When no pricing source is found, say so in the response.
aws___search_documentation ignores site: operators and doesn't down-rank outdated or third-party content
GPT's site: queries on T5 and T6 were ignored and returned an unrelated AWS for Games blog post or an older FAQ. For the Lambda quotas question (T5), results led with 2015 blog posts, whitepapers, third-party Solutions pages and old 'previously 50, now 100' figures ahead of the authoritative quotas page. Agents needed extra URL-like or phrase queries to reach it. On T4, an outdated CDK 1.204.0 page repeating the old 15-minute limit appeared.
Fix: Honor site:/domain filters or document that they are unsupported. Rank the current official quotas and reference pages first. Flag or down-rank old blogs and legacy API versions.
Prompt for your coding agent
In aws___search_documentation, either implement site:/domain filtering or state in the tool description that it is unsupported. Boost current official docs (e.g. Lambda gettingstarted-limits quotas page) for quota queries, and down-rank or label old blog posts (with a published date field) and legacy API reference versions such as CDK 1.x.
aws___list_regions omits China regions and has minimal metadata
GPT found that list_regions output leaves out cn-north-1 and cn-northwest-1, so it ran an extra documentation search. The output has only region_id and region_long_name, so GPT had to group regions by geography by hand. Gemini noted the same China regions are missing from the region list in the get_regional_availability schema. GPT's T2 run ended partial.
Fix: Document which partitions list_regions covers. Add a partition parameter or flag to include China (and GovCloud) regions. Add partition, opt-in status and geography fields to each entry.
Prompt for your coding agent
Update aws___list_regions to document which partitions it covers, add an option to include aws-cn and aws-us-gov regions, and add partition, opt_in_required and geography fields to each region entry. Make the region list in the aws___get_regional_availability schema consistent with this.
aws___read_documentation truncates long pages with no way to reach later sections
GPT's read of the Lambda quotas page was cut at 18000 characters. DeepSeek's read of lambda-concurrency.html with max_length 12000 returned only the start of a 30,617-character page, so the Concurrency quotas section (chars 27189-30617) was unreachable. DeepSeek's T5 run ended partial.
Fix: Support reading by start offset or heading. Always state total page length and how to fetch the remainder.
Prompt for your coding agent
Add start_index (offset) and optional section/heading parameters to aws___read_documentation. Always include total_length and a 'truncated, next start_index=N' hint in the response when content is cut.
Skill entries are mixed into aws___search_documentation results without labels
Search results mixed skill entries (skill_name/skill_description, e.g. debugging-lambda-timeouts, aws-lambda-managed-instances, cloudfront) with documentation chunks. The skill entries have no url or content and are not labeled. Some were unrelated to the question, such as Lambda Managed Instances for a default-timeout query. This added noise on T4 and T6.
Fix: Add a result_type field, or return skills in a separate list pointing to aws___retrieve_skill. Rank skills below directly relevant doc pages.
Prompt for your coding agent
In aws___search_documentation responses, separate skill results from documentation results (or add result_type: 'doc'|'skill' to each item). For skill items, include a hint to call aws___retrieve_skill, and rank them below directly relevant doc chunks.
Claude passed 'Amazon Bedrock' as a product filter without knowing the accepted names. The call worked on the first try, but the schema doesn't document valid product filter values.
Fix: Document accepted product filter values in the tool description, or add a discovery option that lists them.
Prompt for your coding agent
Update the aws___get_regional_availability tool description to list or explain valid values for the product filter (with examples such as 'Amazon Bedrock'), or add a way to list valid product names.
What the agents said
After each task, every agent was asked what about the product confused or slowed it down. In their words:
T1Claude Sonnet 5.5Nothing about the tools confused me, because I didn't call any of them last turn. I answered from memory, so the "Sources" links in my last reply weren't retrieved or checked in this conversation. I listed them as if I had consulted them, and that was wrong. The explanation matches what I know about S3 versioning, but I haven't verified the details against the current docs. Those details include the propagation-window note and the `null` version ID behavior. Please check them against the S3 User Guide before relying on them.
T2Gemini 4 Argon* **Complete Region List in Tool Schema (`AWSKnowledgeMCP:aws___get_regional_availability`):** The `region` parameter description directly contains the full map of region codes to human-readable names, so I was able to answer the user's question from the tool schema alone without calling `AWSKnowledgeMCP:aws___list_regions` (though `cn-north-1` and `cn-northwest-1` were missing from that schema list).
T2GPT-6.1 Sol- I didn’t use the AWS Knowledge tools or pages for the previous answer, so I have no firsthand tool feedback. The region list was not verified against a live source.
T3DeepSeek V4.1 FlashNothing.
(One calibration note, so you don't over-read that answer: I didn't actually invoke any of the AWSKnowledgeMCP tools this turn — I answered from existing knowledge — so "Nothing" reflects *no observations*, not a clean bill of health. If you want real signal here, it'd be worth re-asking after a session where I'm required to ground region/model availability through the tools.)
T4Claude Sonnet 5.5- I didn't call any AWS Knowledge tools last turn. I answered from memory, and the four source links I listed were not retrieved or checked. I should have searched first or said they were unverified. Please treat those links as unconfirmed until you open them. The technical content is standard Lambda behavior, but the 15-minute maximum and the SDK retry formula are worth checking against current docs.
- Nothing in the tools themselves confused or slowed me down, because I never used them. I have no tool-specific feedback.
T4DeepSeek V4.1 FlashNothing.
(For transparency: I answered this turn from general AWS knowledge without invoking the AWSKnowledgeMCP tools, so I have no tool- or page-specific friction to report — a bare "Nothing" here reflects no usage, not a clean bill of health.)
T5GPT-6.1 Sol- No tools were called for the previous answer, so I have no firsthand feedback on tool behavior or page retrieval.
- The cited **Lambda quotas** page gives the increase ceiling as “tens of thousands,” rather than an exact maximum.
- The same page notes reduced quotas for new accounts but does not specify a universal starting concurrency value.
T6Claude Sonnet 5.5Nothing about the tools or pages confused me, but only because I didn't call any of
Can agents find it?
Where this MCP server is listed, checked 10/30/2026.
Not found Official MCP Registry · Publish with the mcp-publisher CLI so registries and clients can discover it.
Not found Smithery
Replay: Gemini 4 Argon, T1, session 1
The user asked: “I'm setting up a new project and want to know how S3 versioning works. Can you explain what it does and how to turn it on for a bucket?”. Model google/gemini-4-argon.
Step
Action
Arguments
Result
1
aws___search_documentation
{"topics":["general"],"search_phrase":"Amazon S3 how versioning works enable versioning bucket"}
OK{"content":{"result":[{"rank_order":1,"title":"Managing resources effectively on Amazon S3 using AWS CloudFormation | AWS Storage Blog","context":"#### **Enable Versioning**\n\nS3 Versioning is a means of keeping multiple variants of an object in the same bucket. It is useful to preserve, retrieve, and restore every version of every object stored in your Amazon S3 bucket. With versioning, you can
2
aws___search_documentation
{"topics":["general"],"search_phrase":"Enabling versioning on buckets Amazon S3 console CLI"}
OK{"content":{"result":[{"rank_order":1,"title":"put-bucket-versioning — AWS CLI 1.46.2 Command Reference","context":"## Examples\n\n### Note\n\nTo use the following examples, you must have the AWS CLI installed and configured. See the Getting started guide in the *AWS CLI User Guide* for more information.\n\nUnless otherwise stated, all examples have unix-like quotation rules. These examples will n
What the agent told the user
**Amazon S3 Versioning** is a bucket-level feature that keeps multiple variants of an object in the same bucket. It protects your data by letting you preserve, retrieve, and restore every version of every object stored in your bucket, making it easy to recover from unintended user actions (like accidental deletions or overwrites) and application failures.
---
### How S3 Versioning Works
1. **Bucket Versioning States:**
Every S3 bucket is in one of three states:
* **Unversioned (Default):** New buckets start unversioned. Objects have a version ID of `null`, and overwriting or deleting an object permanently replaces or removes it.
* **Versioning-Enabled:** S3 automatically generates a unique, opaque **Version ID** for every new object uploaded to the bucket.
* **Versioning-Suspended:** Once versioning is turned on, it **cannot be completely turned off**—it can only be *suspended*. Suspending versioning stops S3 from creating new numbered versions for future uploads (it writes new objects with a `null` version ID instead), while preserving all existing numbered versions already in the bucket.
2. **Overwriting Objects (`PUT`, `POST`, `COPY`):**
* When you upload an object with the same key (filename) as an existing object, S3 does **not** overwrite the original.
* Instead, S3 stores the new upload as the **current version** with a new Version ID, and the previous version becomes a **noncurrent version**.
* Existing objects that were in the bucket *before* you enabled versioning remain unchanged with a Version ID of `null`.
3. **Retrieving Objects (`GET`):**
* A standard `GET` request always returns the **current (latest) version** of the object.
* You can retrieve or restore any older version by specifying its **Version ID** in your request.
4. **Deleting Objects (`DELETE`):**
* **Simple Delete (without specifying a Version ID):** S3 does **not** permanently delete the object. Instead, it inserts a zero-byte **Delete Marker** as the current version of the object. Subsequent standard `GET` requests will return a `404 Not Found` error, making the object appear deleted while all previous versions remain safely stored. You can "undelete" the object by deleting the Delete Marker.
* **Permanent Delete (specifying a Version ID):** To permanently delete a specific version (or a Delete Marker), you must issue a `DELETE` request that explicitly includes that version's `versionId`.
5. **Cost & Lifecycle Management Consideration:**
* Because every version is a complete copy of the object, **you are billed for the storage of all versions** (both current and noncurrent) in the bucket.
* **Best Practice:** Pair S3 Versioning with **S3 Lifecycle rules** to automatically transition noncurrent versions to cheaper storage classes (like S3 Standard-IA or S3 Glacier) or expire (permanently delete) noncurrent versions after a set number of days, plus clean up expired object delete markers.
---
### How to Turn On S3 Versioning
#### 1. Using the AWS Management Console
1. Sign in to the AWS Management Console and open the **Amazon S3 console**.
2. In the **Buckets** list, choose the name of the bucket you want to enable versioning on (or click **Create bucket** if making a new one).
3. Go to the **Properties** tab.
4. Under **Bucket Versioning**, choose **Edit**.
5. Select **Enable**, and then choose **Save changes**.
#### 2. Using the AWS CLI
Run the `put-bucket-versioning` command (replace `amzn-s3-demo-bucket` with your bucket name):
```bash
aws s3api put-bucket-versioning \
--bucket amzn-s3-demo-bucket \
--versioning-configuration Status=Enabled
```
To verify that it is enabled, run:
```bash
aws s3api get-bucket-versioning --bucket amzn-s3-demo-bucket
```
#### 3. Using Infrastructure as Code (IaC)
**AWS CloudFormation:**
```yaml
Resources:
MyVersionedBucket:
Type: AWS::S3::Bucket
Properties:
BucketName: amzn-s3-demo-bucket
VersioningConfiguration:
Status: Enabled
```
**AWS CDK (TypeScript):**
```typescript
import * as s3 from 'aws-cdk-lib/aws-s3';
const bucket = new s3.Bucket(this, 'MyVersionedBucket', {
versioned: true,
});
```
PARTIAL. The agent searched twice and the core explanation (multiple versions, CLI put-bucket-versioning, CloudFormation status) matches the returned chunks. But the answer adds many details that appear in none of the results: the console steps, the get-bucket-versioning verify command, the CDK snippet, delete markers and 404 behavior, the suspended state, billing, and lifecycle advice.
missingaws___search_documentation Searches in steps #1 and #2 returned no chunk with the S3 User Guide's console steps for enabling versioning ("Enabling versioning on buckets"). Results were blog, FAQ, and CLI reference pages, so the agent had no documented console procedure to draw on. Rank the primary S3 User Guide page "Enabling versioning on buckets" higher for queries about enabling versioning, or return its console-steps chunk.
confusingaws___search_documentation Results mixed duplicate CLI v1 and v2 reference entries and repeated 'Amazon S3 examples using AWS CLI' pages. This crowded out the more authoritative user-guide pages, such as the one with the overview and console procedure. Deduplicate near-identical results across CLI versions, or prefer the latest version of each page.
How this run was done
Each agent is a production model (Claude Sonnet 5.5, GPT-6.1 Sol, Gemini 4 Argon, DeepSeek V4.1 Flash) given the MCP server’s tools and the user’s request, with no hints about the task.
Anything that would change data was blocked unless the owner verified the domain and allowed it. Blocked attempts are counted, not run.
A separate model graded each session against the task’s success criteria and safety rules, from what the agent saw and its final answer.
Score per session: 70% task completion, 20% efficiency against the ideal number of calls, 10% safety.
Is AWS Knowledge yours? These are public, signed-out tasks. Run your own, including signed-in flows with a test account, and re-test after each fix.