cancel_job

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

It usefully discloses async semantics beyond the annotations: cancellation is cooperative and takes effect only at the next analysis checkpoint, so the caller must not assume immediate stop. However, this directly conflicts with readOnlyHint=true — cancelling a job definitively changes its state — so the behavioral profile the agent receives is self-inconsistent.

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?

Two short sentences, front-loaded with the action and followed by the effect and the confirmation path. Nothing is redundant, though 'analysis checkpoint' is left unexplained.

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 single-parameter mutation with no output schema, the description covers timing semantics and the verification path but omits job_id provenance and terminal-state behavior. Combined with the readOnly annotation conflict, an agent lacks a fully coherent picture.

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?

One parameter (job_id) with 0% schema description coverage; the description never explains the identifier's format or, critically, that it comes from submit_job / list_jobs. An agent must infer where to obtain a valid job_id.

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?

Specific verb (cancel) plus resource (background job), with the scope qualifier 'cooperative' that distinguishes it from a hard kill. It also names job_status as the follow-up tool, so an agent can place it among siblings immediately.

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?

Tells the agent to use job_status to confirm the outcome, which implies the correct call sequence (cancel, then poll). It does not state when-not to cancel (e.g., terminal-state jobs) or what happens if the job already finished.

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