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

Beyond the annotations, it discloses that cancellation is durable, free, idempotent, cooperative rather than destructive, and changes what work_take and should_continue return. This materially clarifies the destructiveHint=true annotation and prevents the agent from assuming processes are killed.

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 mostly tight and front-loaded, with high-value behavioral detail in each sentence. However, 'FREE and idempotent' is repeated as 'FREE — this tool never charges' near the end, and the HTTP route is optional extra. These are small redundancies, not serious bloat.

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?

The description covers operation purpose, persistent effect, interactions with siblings, non-kill caveat, idempotency, cost, and authentication. Combined with the rich 100%-covered schema, an agent has enough context to call the tool correctly even without an output schema.

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 coverage is 100%, so the schema already documents job_id, reason, and agent_key well. The description adds authentication context and the agent_key fallback option, but this largely mirrors the schema's parameter description rather than introducing new semantics.

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 states a precise verb and resource: it tells every worker on a job to stop by setting a durable stop flag. It also distinguishes itself from related siblings by explaining how work_take and should_continue behave on a cancelled job. This goes well beyond the title and makes the tool's role unmistakable.

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?

It frames itself as the only way to stop running agents and explicitly describes the post-cancel behavior of work_take and should_continue, so an agent knows when to choose it. It also sets expectations by saying it does not kill anything, warning the caller not to expect immediate process termination.

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