AWS MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With zero annotations, the description carries full disclosure burden. The readonly note implies write access is required, but fails to specify overwrite behavior, idempotency, return values, encryption/ACL implications, or error conditions for an operation with significant side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with zero redundancy. First sentence establishes purpose; second states operational constraint. Front-loaded and appropriately sized for the complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Significant gaps remain for a 6-parameter mutation tool: no output schema documentation (success indicators, ETag, VersionId), no mention of S3-specific behaviors like versioning implications, ACL defaults, or server-side encryption options that are critical for S3 put operations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (all 6 parameters documented). Description adds no semantic clarifications beyond schema (e.g., no syntax hints, format examples, or dependency notes between profile/region), warranting baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb 'Upload' plus resource 'S3 object' precisely identifies the operation. Effectively distinguishes from siblings like aws_s3_get_object (download), aws_s3_delete_objects (remove), and aws_s3_list_objects (enumerate).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides one constraint ('Blocked in --readonly mode') indicating mutability, but lacks explicit guidance on when to use versus sibling operations (e.g., overwrite scenarios vs. multipart uploads) and omits permission prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.