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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds substantial context beyond them: cancellation is irreversible (can't be brought back), the in-flight run completes rather than being killed, and no recorded data is deleted. This is exactly the behavioral detail an agent needs before 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?

Three short sentences, each doing distinct work: scope, irreversibility/recovery path, and blast-radius limit. Front-loaded with what is cancelled and what is preserved.

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 destructive operation with no output schema, the description covers scope, reversibility, side effects, and the human-approval precondition. An agent has everything needed to decide and invoke correctly.

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?

Only one parameter and schema description coverage is 100%, so the schema fully documents siteId. The description adds no syntax or format detail beyond it, which is the expected baseline when the schema carries the load.

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 (stop) and a precisely scoped resource (runs that are queued but haven't started, for a given site). This scope distinction separates it cleanly from siblings like list_runs and get_run, and it names trigger_scan as the counter-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?

Gives explicit when-to-use contexts (after a big trigger_scan, or before maintenance), names the alternative for restarting (trigger_scan), and states a precondition (get the user's go-ahead first). Nothing is left to inference.

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