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

The description discloses several behaviors beyond the readOnlyHint annotation: cursor-pagination on (day, value), the definition of membership being tied to mover events, and the 404 response for stale handles with advice to re-read the feed. These are significant behavioral details not captured in 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?

The description is well-structured with a clear lead sentence, then supporting details about pagination and id semantics. Every sentence adds value, and the content is front-loaded with the primary purpose. It is appropriately concise for the complexity involved.

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 the lack of an output schema, the description adequately covers what is needed: it explains pagination, ordering (oldest observation day first), and the staleness behavior. It does not explicitly describe the structure of each returned participant item, but the nature of the tool (listing participant IDs) makes that less critical. Overall, the description is fairly complete.

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 schema already documents all three parameters with descriptions (coverage 100%). The description adds meaningful semantics for `id` by explaining it is a request-lifetime handle from a specific endpoint and that it can go stale, and for `cursor` by noting it is returned as `next_cursor`. This goes beyond the schema's basic type and pattern descriptions.

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's function: 'List participants in a bulk AP migration' and further explains it as 'the drill-down: the participant IDs behind one cohort'. It distinguishes itself from sibling tools by specifying it operates on a cohort handle, and it names the source endpoint for that handle, making the purpose unambiguous.

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 clear context: this is the drill-down for a cohort, and it explains that the `id` comes from `GET /v1/stats/cohort-moves`. It advises not to persist ids because they can go stale. While it doesn't explicitly name alternatives, the context makes the intended use clear.

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