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

Beyond the readOnlyHint annotation, the description discloses crucial behavioral details: it always includes a 'coverage' block indicating how much of the roster is scored and enrichment depth, and it warns that cohort enrichment depth spans ~42 points of catalog_gap, meaning part of any cohort number reflects coverage rather than market reality. It also provides pricing information. This goes far beyond the annotation and is essential for correct interpretation.

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 somewhat long but well-structured: it front-loads the purpose, then adds the live-computation context, the coverage caveat, and pricing. Each sentence serves a purpose, though some redundancy exists (e.g., 'computed live' and 'market-stats sheet' could be combined). Overall, it is efficiently organized and not bloated.

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?

Given that there is no output schema, the description adequately covers the expected output (statistics and coverage block) and the critical caveat about coverage affecting the mean. It also includes pricing. However, it lacks explicit parameter guidance and does not describe the output format in detail, which is a minor gap for a tool with no structured output definition.

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 description does not explain the parameters 'kind' or 'slug' beyond what the enum implies. With only 33% schema description coverage (only 'context' has a description), the description should compensate, but it offers no guidance on how to specify cohort type or slug. It adds no value for parameter usage, leaving agents to guess from the enum values.

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 explicitly states it provides 'the DISTRIBUTION for a whole market' with a specific list of metrics (mean, median, min/max, stdev, etc.) and identifies itself as the 'market-stats sheet from a Trend Report'. This is a clear verb+resource statement that distinguishes it from sibling cohort tools like cohort_scores (individual scores) or cohort_rankings (rankings) by focusing on aggregate distribution statistics.

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 implies when to use it (for market-level distribution stats) but does not explicitly state when not to use it or name alternative tools. The phrase 'UNDERSTANDING — the DISTRIBUTION' suggests a use case, but there is no explicit guidance on selecting this over other cohort tools, leaving the agent to infer from context.

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