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

Goes well beyond the destructiveHint=true annotation by disclosing concrete consequences: an export leaves no file, cancellable and non-cancellable work are distinguished, and generations always run to completion. That last detail alone prevents an agent from wrongly assuming it can stop a generation.

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?

Front-loaded with the action and consequence in a single compact sentence pair, with zero filler. The middle clause about work that 'says so and ends on its own' is slightly oblique in phrasing but still earns its place as a caveat.

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 destructive tool with no output schema, it covers what is destroyed and the cases where cancellation silently fails. It leaves unstated what the tool returns on success versus refusal, which an agent would want given the absence of 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?

Only one parameter with 100% schema coverage, so the schema already explains job_id as the id returned by a Cardboard tool. The description adds no further meaning, which is the expected baseline for a fully documented single param.

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?

Specific verb 'stop' plus resource 'a running job' with a concrete example ('an export stops and leaves no file'). It does not name a sibling (e.g. job_status or generation_status) to contrast against, so differentiation is implicit 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 description implies the condition for use (a job is running and you want it stopped) and warns that some work cannot be stopped, but never points to job_status or generation_status for checking state first, nor states what to do if cancellation isn't possible.

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