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

Annotations already indicate a state-changing (readOnlyHint=false), non-destructive operation. The description adds the important no-op edge case beyond those hints, but it does not disclose return values, error behavior, or cancellation semantics for a running run.

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 deliver the core action and the critical edge case with no unnecessary filler. The description is well front-loaded and appropriately sized for the tool's simplicity.

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 tool with no output schema, the description covers the action and the notable already-stopped case. It could mention success/error responses, but the operation is simple enough that an agent has sufficient information to select and invoke it.

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 input schema fully documents run_id as the run's unique identifier, so the schema carries the parameter semantics. The description adds no additional parameter meaning beyond what is already present, warranting the baseline score for full schema coverage.

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 opens with a specific verb-object pairing, 'Stop an agent run', that clearly names the resource and action. It distinguishes this tool from startRun/getRun and from other stop* siblings that act on different resources.

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 no-op clause provides clear contextual guidance: if the run is not currently running, the call has no effect, so an agent doesn't need to be concerned about stopping an already-finished run. It does not explicitly list alternatives, but the simple and complementary nature of the action makes the intended use clear.

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