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

Annotations already declare destructiveHint=true and idempotentHint=true, so safety and repeatability are covered. The description adds genuinely new behavior: the job's price is refunded to the balance 'at once', telling the agent the side effect is financial and 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?

One sentence, front-loaded with the action and its precondition, with the refund outcome trailing. Nothing is padding.

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 mutation with no output schema, the description covers the eligibility precondition and the refund side effect, which is most of what an agent needs. It does not say whether an ineligible job returns an error or what the response body contains, a minor gap.

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% and the single job_id parameter is already documented with its cloud_/motion_ prefixes. The description adds no format, validation, or lookup detail beyond the schema, so baseline 3 applies.

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?

Names a specific verb (cancel) with the exact resource and scope: a restore or clip whose file was never uploaded. An agent can distinguish it from create_restore, start_clip, and start_restore without opening any schema.

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 'whose file was never uploaded' implicitly scopes usage to unstarted jobs and rules out cancelling in-progress work, which is real context. It never names an alternative tool or states what to do if the job has already started, so it falls short of a full when/when-not statement.

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