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

Annotations already carry destructiveHint and idempotentHint; the description reinforces idempotency and adds that the operation is 'Authenticated, owner-scoped,' which is useful safety context. It doesn't detail failure behavior, but the annotations plus output schema cover the main safety traits.

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?

Three compact lines, front-loaded with the action and target; the trailing 'Authenticated, owner-scoped, idempotent' adds safety-relevant facts without fluff.

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 single-parameter destructive action, the description is nearly complete: it covers target, state, authentication scope, and idempotency, and an output schema exists so return values don't need to be described. The main omission is source of job_id, but that's minor for this simplicity.

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?

Only parameter is job_id; the description doesn't explicitly document it, and schema coverage is 0%. The phrase 'STORM or Dataset agent job' gives some context that job_id is the identifier of such a job, but doesn't say how to obtain it or validate it, so compensation for the low coverage is partial.

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?

Description uses a specific verb ('Cancel') and identifies the exact target: 'queued or running STORM or Dataset agent job.' This clearly differentiates it from status/research siblings like agent_job_status and research_status.

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 clear context on when to call it — for queued/running STORM or Dataset jobs — and the owner-scoped note implies only the owning user should invoke it. It doesn't name an alternative, but there is no other cancel-job sibling, so the routing is unambiguous.

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