Cancel a run

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true, so the safety profile is covered structurally. The description adds a genuine consequence beyond those flags—'Stops further usage by that run'—telling the agent what resource consumption ceases, which is the kind of 'what gets destroyed' context the annotations do not spell out. It still omits the outcome for a run that is already terminal.

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, zero filler, with the action and its scope front-loaded before the effect. Nothing could be trimmed 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 no output schema, the description plus annotations cover the essentials an agent needs to call it safely. The remaining gap is minor: it does not say what happens when the target run is already complete or unknown to the cancellation path.

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%: the single 'run' parameter already documents that it accepts a run ref or numeric id. The description adds nothing about the parameter, so the baseline 3 applies—the schema does all the work.

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 names a specific verb and resource ('Cancels ... a run') and narrows the scope to 'queued or running' runs, which lets an agent tell it apart from start_run, rerun_failed, and wait_for_run by name alone. It stops short of explicitly contrasting itself with those siblings, so it is clear but not fully differentiated.

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?

Applicability is implied by state: only a queued or running run can be cancelled. There is no explicit when-to-use guidance, no statement of what to do instead once a run has finished or failed, and no mention of the alternatives (rerun_failed, start_run) that an agent might confuse this with.

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