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

The annotations already establish that this is a mutating, non-destructive, non-idempotent, open-world operation, so the safety profile is covered. The description usefully adds the state precondition (only queued/running jobs), but does not say what state the job ends in, whether partial output is preserved, or whether cancellation is immediate or graceful.

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 with zero filler; the core action and the key state restriction are both front-loaded. 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?

For a single-parameter mutation with an output schema and full schema coverage, the description covers the essential precondition and scope. The remaining gap is routing information against sibling tools and the post-cancel job state, both minor given the structured fields.

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 coverage is 100% and the schema's own job_id description ("returned by save_run or simulate_strategy") is more informative than anything in the tool description. The description adds no meaning about job_id beyond the schema, so the baseline of 3 applies.

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?

"Stop a queued or running job of the caller" gives a specific verb (stop) and resource (job) plus scope (the caller's own jobs). It is clear on its own, but it never distinguishes itself from similarly-named siblings such as delete_run, close_paper_run, or get_job.

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 implies the use case (cancelling work you no longer want) and adds a real selection rule: a finished job cannot be cancelled, so the agent should check state first. It names no alternatives, though, so an agent cannot tell from this text whether to use delete_run or close_paper_run instead.

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