cancel_audit

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

Goes well past annotations by explaining the actual mechanism: a cancel request is queued on the audit-dispatch outbox, a background worker signals the session, and the orchestrator's own /audit-cancel cleanup runs ('no hard kill'). It also discloses the response shape (per-project status of 'queued' or 'unknown_project'), which is exactly the kind of context annotations cannot convey.

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?

Front-loaded with the action and scope, then the mechanism, then the result format. Four sentences all carrying information; the outbox/worker sentence is dense but earns its length by explaining the non-destructive semantics.

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?

With no output schema, the description usefully explains the returned per-project statuses, and the async cancel mechanism is fully described. The only real gap is the undocumented `as_agent` parameter and the ambiguity around whether `projects` is mandatory.

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 0%, so the description must compensate, and it does well for `projects` — accepting a list of slugs or ids and noting each is resolved. However, `as_agent` is never mentioned, and the schema marks no parameters required while the description implies `projects` must be passed.

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 and resource ('cancel a running audit') plus scope ('one or more projects'), and the 'Admin:' prefix signals the privilege class. It is trivially distinguishable from request_audit and the other lifecycle siblings.

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 admin framing and 'cancel a running audit' imply the situation, but there is no explicit when-to-use/when-not, no mention of what happens if the audit is not running, and no named alternative. Usage must be inferred.

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