vibe_cancel

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

With no annotations, the description carries the full behavioral burden and does disclose two useful facts: the operation is a mutation that terminates running work, and the worktree survives. It does not say whether a running job is killed gracefully, what permissions are needed, whether the call is idempotent, or whether an error is returned for already-completed jobs.

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, zero filler, and the state distinction is front-loaded before the artifact-preservation detail. Nothing is repeated and nothing is padded.

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 no annotations and no output schema, the description covers the core action and one side effect, but leaves the agent guessing about the return value, failure modes, and id provenance. It is adequate to call the tool but not 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?

There is a single required job_id parameter with 0% schema description coverage, so the description must compensate and largely does not: it never says where job_id comes from (presumably vibe_submit), what format it takes, or how an invalid or unknown id is handled. It only implies that the id must refer to a queued or running job.

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?

The description names a specific verb pair (cancel/kill) and the resource (a queued or running job), and its state-dependent framing makes the tool's scope immediately clear. It does not reference any sibling, but none of vibe_submit, vibe_wait, vibe_result or vibe_apply overlaps with cancellation, so disambiguation is effectively implicit rather than stated.

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 'a queued job' versus 'a running one' tells an agent the two contexts in which to call it and what happens in each. It stops short of exclusions or follow-up guidance, such as whether to read results via vibe_result afterwards or what to do if the job has already finished.

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