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

Annotations already declare idempotentHint=true, destructiveHint=false and readOnlyHint=false, so the description's job is to add context — and it does: it names the required projects:write permission and discloses that history, prior usage and uncertain outcomes are preserved. The phrase 'uncertain outcomes' hints that cancellation may race with in-flight work. It stops short of saying whether cancellation is immediate or lands in a pending state, which is the one gap.

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?

A single compact sentence with the core action front-loaded, followed by the permission and retention clauses. Slight redundancy in naming 'reason and idempotency_key', which the schema already carries, but no wasted sentences.

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 3-required-param mutation with annotations covering the safety and idempotency profile and no output schema, the description supplies the remaining essentials: permission requirement, retention semantics, and idempotency expectations. An agent can call this correctly without further reading.

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?

With only 33% schema description coverage, only idempotency_key is documented structurally, so the description should compensate more. It names 'reason' and 'idempotency_key' as the inputs but adds no meaning beyond the schema — no explanation of the rsq_ id format, no guidance on what makes a useful reason, and no note that all three fields are required.

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 ('Request cancellation') and resource ('your own work' — the resident request), with scope limited to the caller's own records. It is clearly distinct from cancel_investigation, though it never names or contrasts a sibling explicitly.

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 phrase 'your own work' implies you cannot cancel others' requests, and 'Requires projects:write' gives a prerequisite. But there is no explicit when-to-use vs when-not guidance, no statement about which request states can be cancelled, and no pointer to an alternative such as appeal_outcome or get_resident_request for inspecting first.

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