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

Annotations provide readOnlyHint=true, so the safety profile is known. The description adds valuable behavioral context: pagination behavior (byte-budgeted chunks, complete flag, next_cursor), pricing tier, and the fact that large cohorts are chunked. It also clarifies the 'context' parameter is never used for ranking. This goes beyond the annotation without contradicting it.

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 dense but well-organized: purpose first, then pagination, then pricing. Every sentence earns its place. It is slightly long but each clause carries information. The front-loading of 'UNDERSTANDING' and the core purpose is effective. Minor deduction for the pricing sentence being somewhat tangential to tool invocation.

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 paginated list tool with no output schema, the description covers the essential invocation flow: what it returns, how to paginate, and how to handle the context parameter. It does not describe the exact shape of the response items, but the absence of an output schema makes that a minor gap. The pricing and inclusion info is a bonus. Overall, an agent can call this tool correctly with the information given.

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 coverage is 50% (cursor and context have descriptions; kind and slug do not). The description compensates by explaining the pagination semantics of cursor ('call again with cursor set to next_cursor') and the purpose of context ('why you are asking... never included in the answer'). It does not explain kind/slug values, but those are fairly self-evident from the enum and the tool's purpose. The description adds meaning beyond the schema for the pagination flow.

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 opens with a clear verb and resource: 'UNDERSTANDING — what every member of a cohort actually publishes: artifact counts by type plus the agent-readiness dimensions each one satisfies.' It names the specific output (capability matrix) and distinguishes it from sibling tools like cohort_stats or cohort_scores by focusing on artifact counts and agent-readiness dimensions. The title 'Cohort capabilities' is reinforced, not merely restated.

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 pagination instructions ('while complete is false, call again with cursor set to next_cursor') and pricing context ('Priced B2... $0.05 per call... included in Understanding and Influence'). It does not explicitly name alternative tools or when-not-to-use, but the context of 'capability matrix behind a market report' implies its use case. Slight gap: no explicit exclusion of when to use cohort_stats or cohort_scores instead.

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