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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds material context beyond them: the revocation of invitations the cohort created (a downstream side effect) and the eligibility constraint on cohort state. It doesn't state whether deletion is reversible or what errors arise on disallowed states, so 4 rather than 5.

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?

One sentence, front-loaded with the action, then the side effect, then the eligibility limit. No waste.

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 destructive single-parameter tool whose annotations already cover the safety profile, the description covers action, side effects, and eligibility. Only the irreversibility/error behavior is unstated, which is 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 0% for the single cohortId parameter, so the description carries the burden; it implies the target is a cohort preparation but adds no format or identification detail (UUID, where to obtain it). Adequate but thin.

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?

States a specific verb (Delete) and resource (next-cohort preparation) plus the scope of eligibility (unlaunched) and side effect (revoke invitations). An agent can distinguish this from siblings like cohorts_manage or remove_member without opening any schema.

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?

Explicitly states the exclusion: cannot delete a launched or historical cohort, which is a real when-not-to-use rule. It doesn't name an alternative tool for those cases, so it falls short of 5, but the condition that gates invocation is unambiguous.

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