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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally; the description adds the concrete consequences (pending items never run, executed items remain, cannot be undone). It does not restate the idempotency-key retry semantics, but those live in the schema description, so this is a modest gap rather than a miss.

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?

Front-loaded with the operation and its consequence, and every clause is decision-relevant. Minor redundancy between 'Cannot be undone' and 'Irreversible for the pending items' costs a point, but there is 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 destructive, irreversible tool with a full output schema and complete annotations, the description supplies the consequence model and the pause_job alternative an agent needs. What is missing — post-cancellation job state and response shape — is covered by the output schema.

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 100%, including job_id provenance ('as returned by create_job or list_jobs') and a full idempotency_key explanation, so the schema carries all parameter meaning. The description adds nothing about parameters, which is the correct baseline when coverage is complete.

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+resource ('Cancel a job') and immediately clarifies scope: pending items will never run, executed items are unaffected. It explicitly contrasts with the sibling pause_job, so an agent can distinguish it from create_job/list_jobs/get_job without opening schemas.

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?

Explicitly routes to the alternative: 'To stop temporarily use pause_job.' It also adds a when-to-use guardrail — 'confirm with the user' — for an irreversible action, which is exactly the decision context an agent needs.

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