cancel_task

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

With no annotations, the description carries the full burden and does add real behavioral detail: the child process is also terminated and job files/worktree are intentionally preserved for inspection. However, it omits permissions/auth needs, whether cancellation is graceful or immediate, and what happens when the task has already completed or failed.

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 tight sentences with zero filler. The action and its scope are front-loaded, and the second sentence delivers the non-obvious side effect about retained files.

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 state-mutating tool with no annotations and no output schema, the description covers the core action and cleanup semantics but leaves open the return value, idempotency, and behavior against already-finished tasks. These are gaps an agent may hit in practice.

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 0%, so the description would need to compensate, but it says nothing about task_id's format or where to obtain it. The single required parameter is close to self-evident from its name, so this is adequate rather than harmful.

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 gives a specific verb (cancel) and resource (delegated task, plus its child process), and the phrase 'queued or running' scopes which tasks are affected. It is distinguishable from submit_task/get_task by the verb alone, though it never names a sibling explicitly, which keeps it just short of a 5.

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?

'Queued or running' implicitly tells the agent the applicable task states, but there is no explicit guidance on when to prefer this over siblings, no mention of what to do if the task is already terminal, and no prerequisites. Usage is implied rather than stated.

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