AWS MCP Server

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

No annotations provided, so description must carry full burden. It omits critical behavioral details: no mention of read-only/safe operation nature, pagination behavior (ListMetrics API is paginated), or what the return structure contains (list of metric definitions with dimensions).

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?

Single sentence of 9 words with no redundancy. Front-loaded action verb and immediately scoped resource. Every word earns its place despite the information density.

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?

With 5 filter parameters and no output schema, the description is minimally adequate. It covers the core action but leaves gaps regarding the optional nature of filters, expected return values, and AWS-specific pagination limits that would help an agent invoke this correctly.

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%, so the schema fully documents all 5 parameters. Description adds minimal semantic context beyond the schema ('namespace or resource' loosely maps to parameters) but baseline 3 is appropriate when schema does the heavy lifting.

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?

States specific verb 'List' and resource 'CloudWatch metrics' clearly. Mentions scoping 'for a namespace or resource' which hints at filtering capabilities. However, it does not explicitly distinguish from siblings like 'get_metric_data' or 'get_metric_statistics' which retrieve actual data points rather than metric metadata.

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 no guidance on when to use this tool versus alternatives (e.g., when to list metrics vs. retrieving statistics with get_metric_statistics). Does not mention that all parameters are optional or typical prerequisite workflows like discovering namespaces first.

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