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

Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context: the org → project → spec cascade, grouping by status code, and that this tool does not return policy definitions. No contradictions with annotations.

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?

Three concise sentences, each earning its place: what the tool returns, the key alternative, and the definition-listing alternative. Slightly redundant with the schema by saying 'Takes an endpointId' when specId is also required, but overall tight and well-structured.

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?

For a read-only two-parameter lookup with no output schema, the description covers response grouping, cascade behavior, alternatives, and a prerequisite. It does not detail the exact response format, but enough is provided for correct selection and invocation.

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 baseline is 3. The description adds the 'whole endpoint' vs 'one response' nuance for endpointId, but it does not really elaborate on specId beyond the schema. It is adequate but not a major value-add.

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 clearly states a specific verb ('Get'), the resource ('headers that apply to a WHOLE endpoint'), the grouping ('by status code'), and the cascade context. It explicitly distinguishes this tool from get_resolved_headers, so an agent can select it correctly.

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 gives explicit when-to-use guidance: use this for whole-endpoint headers, use get_resolved_headers for a single response, and use list_header_policies for policy definitions. It also notes the project context prerequisite, leaving little to inference.

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