task_cancel

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

The annotations already mark the tool as destructive, non-idempotent, and not read-only. The description adds useful operational context about lease requirements for running tasks and which task states can be cancelled by id alone, going beyond what the annotations and schema together provide.

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 sentences, front-loaded with the core action and followed by the key state-dependent constraint. Every sentence earns its place with no filler.

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 two-parameter mutation tool with no output schema, the description covers the main operational nuance: when a lease is needed and when cancellation can be done by id. Annotations cover the destructive safety profile, so remaining gaps such as irreversibility details are not critical.

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 50%: leaseId is documented in the schema, while id has no schema description. The description says tasks can be cancelled by id, implying id identifies the task, but it adds no format, origin, or constraints for id and largely repeats the leaseId requirement already present in the schema.

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 states a specific verb and resource: 'Cancel a durable task.' This clearly distinguishes the operation from sibling task tools such as task_submit, task_claim, task_update, and task_verify. An agent can identify the core action without opening the schema.

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 description gives state-dependent usage context: a running task requires its current lease, while queued/verifying/repairing tasks can be cancelled by id. It does not explicitly name alternatives or when not to use the tool, but the cancellation conditions are clear enough to guide invocation.

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