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

Annotations already declare destructiveHint=true, so the description does not need to restate destructiveness. It does add the useful behavioral constraint that only running jobs can be stopped, implying that already-completed or queued jobs are not the target. Still, it does not describe side effects like whether job state becomes canceled or whether resources are freed, so value beyond annotations is moderate.

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?

The description is exceptionally concise: four words with no filler. It front-loads the core action and leaves parameter details to the schema, which is the ideal structure for a simple tool.

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, single-action tool with a clear output schema and destructive annotation, the description is mostly complete. An agent can correctly invoke it with run_id and understand it is destructive. It could add a note about cancellation being irreversible, but annotations already cover the destructive hint.

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?

The schema already provides 100% coverage: run_id is required and described as 'The run_id returned by runs.launch.' The description adds no parameter-level detail beyond this, so baseline 3 is appropriate.

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 'Stop a running job' uses a specific verb and resource, and clearly distinguishes runs.cancel from sibling tools like runs.launch, runs.get, and runs.report. An agent can immediately understand this is the cancellation operation.

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 when to use the tool: when a running job needs to be stopped. However, it does not explicitly state when not to use it or mention alternatives such as runs.get for checking status or runs.report for outcomes. Usage context is present but only implicit.

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