cancel_task

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

With zero annotations, the description carries the full burden, and it does disclose one valuable effect: the worktree is retained for inspection, implying it is not deleted. It says nothing about whether cancellation is reversible, whether partial work is discarded, what permissions or auth are needed, or whether the call waits for termination.

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, with the effective scope front-loaded and the side effect second. Nothing could be removed without losing information.

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?

An output schema exists, so the description needn't explain return values, and the core action plus the retained-worktree behavior is covered. The remaining gap is that this is an unannotated state-mutating tool whose parameters, idempotency, and permission requirements go unexplained.

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% and the single parameter task_id is never mentioned in the description, so the agent gets no meaning beyond the bare property name and string type. Since the schema does no work here, the description should have identified what identifier is expected and where to obtain it.

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 plus resource ("Cancel a running or waiting ticket") and even narrows the applicable states, so the action is unambiguous. It loses a point for calling the resource a "ticket" when the tool and sibling names use "task", and for not distinguishing itself from nearby siblings like get_task_status or dispatch_task.

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 "running or waiting" implicitly tells the agent which task states are eligible for cancellation, which is real usage guidance. However, there is no statement of when not to cancel, whether a stopped/completed task can be passed, or which sibling to use instead for inspecting status before cancelling.

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