Cohort report across posts

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

Annotations (readOnlyHint=true) already indicate it's a read operation. The description adds that it runs the verdict engine, returns a sorted table, and can use sitemap_url or explicit urls. This provides useful behavioral context beyond annotations. No contradiction.

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 two sentences, directly stating the action and a practical use case. No redundant information, front-loaded with the core functionality. Efficient and clear.

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 an output schema exists and annotations are present, the description provides a high-level overview and a use case. However, it lacks explanation of how cohort filtering works with the available parameters (e.g., the missing tag parameter). Overall, reasonably complete but a minor gap.

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 low (40%). The description adds meaning by explaining min_age_days as a filter and mentioning 'tag' (though not in schema), but does not elaborate on window, limit, or the interaction between urls and sitemap_url. Partially compensates for low schema coverage but leaves gaps.

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 the tool 'Run the verdict engine across a cohort... return a ranked table sorted by verdict priority then confidence'. The title 'Cohort report across posts' aligns, and the practical use case differentiates it from siblings like posts.verdict (single post) or posts.list (listing without verdicts).

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 a concrete use case: 'which three posts should I refresh this week?' indicating when to use (cohort evaluation for refresh decisions). It mentions filtering by tag and min-age, but the schema lacks a tag parameter, slightly reducing clarity. No explicit exclusions or alternatives are provided.

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