AWS MCP Server

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

No annotations provided, so description carries full burden. Only discloses that it is blocked in readonly mode (implying it's a write operation). Fails to mention critical mutation behaviors: invalidations are asynchronous with propagation delays, incur AWS costs, have limits (3 concurrent per distribution), and return an invalidation ID for tracking.

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 waste. First sentence states purpose upfront; second provides operational constraint. Every element earns its place.

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?

Mutation tool with side effects (costs, async propagation) and no output schema. Description should disclose return value structure (invalidation ID/status) and operational characteristics ( propagation time, costs) but does not. Relies entirely on parameter schema and name for context.

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% with clear descriptions for all 4 parameters (profile, region, distribution_id, paths). Description adds no additional semantic context beyond the schema, which is adequate when schema coverage is high.

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 specific verb ('Create') + resource ('cache invalidation') + target ('CloudFront distribution'). Effectively distinguishes from read-only siblings like aws_cloudfront_list_invalidations and aws_cloudfront_get_distribution.

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?

Mentions '--readonly mode' constraint indicating when the tool cannot be used, but lacks explicit guidance on when to prefer this over TTL expiration or alternative cache busting strategies. Usage is implied by the operation name but not fully contextualized.

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