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

Annotations already flag destructiveHint=true, so the baseline is met; the description goes beyond by disclosing the cascade (open subtasks are cancelled too), that the reason is persisted, and that a COMMANDER agent must supply commander_grant_id. It does not explain irreversibility or what happens to the cancelled task record afterwards.

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?

Extremely dense and front-loaded: scope, cascade, and the auth requirement come in that order with no filler. The telegraphic style ('people may cancel any') costs a little precision but nothing is wasted.

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?

With an output schema present the return value needn't be described, and the destructive/mutation semantics are covered by annotations plus the cascade note. Against four input parameters at 0% schema coverage, though, the missing semantics for task_key and the version-conflict behavior leave a real gap for a destructive operation.

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 carries the full burden, yet it only illuminates two of four parameters: reason (recorded) and commander_grant_id (required for commander agents). task_key and especially expected_version, which implies optimistic concurrency, are left entirely unexplained.

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 opens with a clear verb+resource ('Cancel a task') and immediately qualifies scope (owner-only unless an admin, and only while unheld), which distinguishes it from update_task or set_status. The only weakness is the loose phrasing 'people may cancel any', which leaves the privileged role ambiguous.

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?

It states the preconditions for calling (ownership/privilege, task not held by someone else) which is real when-to-use guidance. However, it never names an alternative tool or says when cancellation is the wrong choice versus updating, reassigning, or handing off a task.

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