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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond annotations by specifying owner-scoping and excluding raw headers/request bodies, which are meaningful privacy and scope details.

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?

The description is a single, well-structured sentence that front-loads the action and outcome. Every word earns its place with no fluff or repetition, making it highly concise.

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?

The tool is simple with two optional parameters and no output schema. The description explains the purpose and key constraints, but it does not describe what metrics are returned or the overall response structure, leaving some gap in completeness for an agent without prior assumptions.

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?

The input schema has 0% description coverage, and the description does not mention the parameters or their semantics. While names like windowHours and topMethodsLimit are suggestive, the description does not compensate for the lack of schema descriptions, leaving ambiguity about their exact meaning and usage.

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?

The description uses a specific verb ('Return') and clearly identifies the resource ('owner-scoped aggregate MCP audit metrics'). It explicitly distinguishes from sibling tools by stating it excludes raw headers and request bodies, contrasting with mcp.audit.list.

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?

The description clearly implies when to use this tool: when aggregate metrics are needed rather than raw audit events. The contrast 'without raw headers or request bodies' and the sibling name mcp.audit.list provide strong context, though no explicit alternative is named.

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