cancel_job

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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the risk profile is covered; the description adds genuinely new context by disclosing that partial-run evidence is preserved and that the effect differs for queued vs. actively running work. It stops short of saying whether the cancellation is graceful or immediate.

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 front-loaded sentence with no filler; the action comes first and the side-effect clause follows. It is efficiently sized, though the two-branch distinction is compressed into one clause rather than structured.

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 destructive tool, everything an agent needs is present: annotations carry the safety profile, the schema fully documents job_id, and an output schema exists so return values need no prose. The description contributes the one non-obvious fact — that evidence survives cancellation.

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 100% and the job_id field already explains its provenance ("returned by start_separation or an audio tool"). The description adds nothing about the parameter, which is fine at baseline 3 but no better.

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 pair ("stop" / "terminate") against a specific resource (queued work / native worker), and clarifies that both a queue-level and a process-level cancellation path exist. It is clearly distinguishable from the closest siblings (get_job, list_jobs) although it does not name them 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 two branches (queued vs. running) imply when each behavior applies, but the description never states prerequisites, whether to check job state with get_job first, or what is not cancellable. Usage is inferable rather than stated.

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