cancel_request

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description doesn't need to restate mutation. It adds valuable behavior beyond the annotations: the two return values ('cancelled' vs 'not_cancellable') and the fact that already-done requests are tolerated, which concretely explains the idempotency semantics. No contradiction with the annotation set.

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 with each one earning its place: the core action, the underlying endpoint for traceability, and the expected return values. The most important behavioral signal is front-loaded in the first sentence. There is zero filler.

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 low-complexity tool with two simple required parameters, the description covers the essential flow: target state, accepted outcome, and already-complete outcome. Annotations cover safety. Minor gaps remain — no error behavior for invalid/nonexistent request IDs and no indication of how request_id is obtained — but nothing that blocks correct invocation in the main path. Given low complexity, this is nearly 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?

Schema description coverage is effectively 0% — properties have only titles ('Request Id', 'Deployment Id') with no descriptions. The description partially compensates by embedding both parameters in the endpoint URL, showing deployment_id identifies the deployment and request_id identifies the request to cancel. However, it provides no format, type nuance, or guidance on obtaining valid IDs, so it doesn't fully carry the documentation burden.

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 action ('Cancel') against a clearly scoped resource ('a queued or running request'), and the endpoint path (/prod/v1/deployments/{deployment_id}/requests/...) distinguishes it from the similarly-named sibling cancel_training_job, which targets training jobs rather than deployment requests. The scope qualifier (queued or running) adds precision beyond the bare name.

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 intended use case is implied by the first sentence — use this when a deployment request is queued or running and needs to be cancelled — but there is no explicit when-not-to-use guidance and no comparison against cancel_training_job, which is the most likely confusion point. The endpoint makes routing inferable, but the description leaves the alternative selection entirely to interpretation.

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