cancel_audit

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

With no annotations, the description carries the full burden and does well: it discloses the async queue path (audit-dispatch outbox), the background worker signaling the session, that cancellation is cooperative rather than a hard kill, and the orchestrator's /audit-cancel cleanup. It stops short of stating auth/permission requirements precisely or idempotency/behavior for already-finished audits.

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?

Three sentences, front-loaded with the purpose, then parameter instruction, then behavior. Dense but each sentence carries information; the outbox/worker detail is slightly verbose but earns its place as behavioral disclosure.

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?

No output schema, so the description helpfully states the return shape (per-project status 'queued' or 'unknown_project'). For a two-param, no-annotation tool the picture is nearly complete; the gap is the unexplained `as_agent` parameter and the fact that `projects` is described as needed while required is empty.

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% and the schema only declares bare types, so the description must compensate. It explains that `projects` accepts a list of slugs or ids, but the casings differ (`projects` vs schema's `Projects`) and `as_agent` is never described, leaving one of two parameters undocumented.

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 a privilege qualifier ('Admin:'). It is trivially distinguishable from its inverse sibling request_audit without opening a 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?

The 'Admin:' prefix and 'running audit' phrasing imply the context for use (an in-progress audit needing cancellation by an operator), but no explicit when-to-use/when-not guidance or named alternative is given. 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.