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

Beyond the annotations already disclosing destructive and idempotent behavior, it states the partial refund policy and that completed work remains paid for and stays in results. It also notes the operation is free, which is useful non-obvious context.

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 valuable: the operation, the refund semantics, and the cost. The core intent appears first and there is no filler.

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 an output schema, the description covers the most important behavior and economics. It could mention what happens if the job is already complete or already canceled, but idempotentHint partially covers that.

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?

The tool description does not add param details, but the schema already provides full coverage: job_id is described as 'id returned by submit_transcripts_job'. The description's general reference to 'a batch job' aligns with this parameter, so no real gap exists.

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 starts with 'Cancel a batch job', clearly naming the action and its target. It is easily distinct from the get/search/submit siblings, and the title reinforces the 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?

The refund condition ('Credits are refunded ONLY for videos not started yet') gives a concrete rule for deciding whether a cancellation is still worthwhile. It implies this should be used when the caller wants to stop a previously submitted batch job, though it does not explicitly list when to avoid cancellation.

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