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

Goes well beyond the annotations (destructive/idempotent/not-readonly) by disclosing the exact cancellation semantics: a rendering run stops after its current step with status 'cancelling' then 'cancelled', a queued run closes immediately at no cost, and already-finished steps are kept but not refunded. This is precisely the behavioral detail an agent needs before firing a destructive call.

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 core action and scope, then layered with outcomes and the scope requirement. Everything earns its place, though the density of clauses makes it slightly heavier than a tight two-sentence definition.

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 tool with no output schema, the description covers the trigger, the effect on both running and queued runs, cost/refund behavior, status observability via get_run, the runId default, and the required pipelines:run scope. Nothing material is missing.

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%, so the schema already documents both runId (omit for newest running run) and pipelineId. The description echoes the omit-runId default and the pipelineId origin, adding little beyond the structured fields, so the baseline 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?

States a specific verb (cancel/stop) and resource (run), and explicitly scopes it to runs started by run_pipeline, assemble_video, or edit_asset. An agent can distinguish this from get_run or any of the creation siblings without opening a 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?

Explicitly states when to use it ('when the person asks to cancel, stop or kill a render'), including an edge trigger ('stop, that's wrong'). It also points to get_run for observing the resulting status, giving both the trigger condition and the follow-up tool.

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