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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds genuinely non-obvious context — a stopped run 'is not counted' — which tells the agent the effect on usage/billing, though it omits what happens if the run is already terminal or whether the stop is immediate.

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, no filler, with the applicability scope front-loaded before the side-effect note. Every clause carries information an agent can act on.

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 one-parameter tool with rich annotations and no output schema, this is close to sufficient. The remaining gap is edge-case behavior — whether stopping an already-completed run errors and whether the stop is synchronous — but nothing essential to invoking it correctly 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?

There is a single required parameter documented at 100% schema coverage, so the schema already carries the semantics of runId. The description adds no format, source, or validation detail beyond what the schema states.

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 gives a specific verb and resource ('Stop a ... run') and narrows the scope to runs that are 'queued or running,' which tells an agent it applies to non-terminal states only. It never names a sibling (e.g., wait_run or get_run), so differentiation is inferred rather than stated.

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 phrase 'queued or running' implies when the tool is applicable, and the description says nothing about when it is not (e.g., already-finished runs) or what alternative to use for observing a run instead of stopping it. Usage is implied rather than prescribed.

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