jobs_cancel

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

Annotations already declare non-readonly, non-idempotent, open-world, non-destructive, so the safety profile is covered; the description adds real value by explaining the queued-vs-running asymmetry and that provider-side side effects already applied are not rolled back. It does not describe what the call returns (a confirmation vs. a job record) or whether repeated cancels fail, which keeps it from a 5.

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 short sentences, each carrying distinct information: the two cancel modes, the preferred triggering context, and the rollback caveat. Nothing is repeated and the core behavior is front-loaded.

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 one-parameter mutation with full annotation coverage and no output schema, the description covers the essential decision points. The only meaningful gap is the return/confirmation semantics, which an agent must currently infer.

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 100% with a single required job_id already documented as "Job id to cancel." The description adds no format, provenance, or sourcing hint (e.g., where to obtain a job id) beyond what the schema supplies, so the baseline 3 applies.

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 job) and splits it into two distinct behaviors: queued jobs cancel immediately, running jobs get a cancel request. That distinction alone lets an agent predict the outcome, and the mention of jobs_enqueue/chat_ask ties it to the work it undoes.

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?

"Prefer when stopping work started via jobs_enqueue/chat_ask wait:false" gives a concrete triggering condition and names the producing tools. It stops short of stating when NOT to cancel or what to do if the job already finished, but the context is clear enough to act on.

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