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

Annotations already declare destructiveness and idempotency. The description adds behavioral context by specifying that only the export is cancelled and the source video is retained, and instructs to continue polling until a terminal state. This goes beyond the annotations by clarifying the scope of destruction and post-call behavior.

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?

Two concise sentences, front-loaded with the action, and no fluff. The polling instruction is an essential behavior. Highly efficient and well-structured.

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 simple single-parameter tool with an output schema, the description covers the essential behavior (cancel, retain source, poll). It could explicitly mention the task_id parameter meaning, but the output schema and annotations cover other aspects. It is fairly complete, though a small gap remains.

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 schema has 0% description coverage for the only parameter (task_id), and the description does not explain that task_id is the identifier of the export to cancel. It mentions 'owned export' but does not connect it to the parameter. With low schema coverage, the description should compensate, but it omits any parameter guidance.

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 specific action ('cancel'), the resource ('owned export'), and a key constraint ('retain the source video for another export'), distinguishing it from other cancellation tools in the sibling list like cancel_animation. It is unambiguous about what the tool does.

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 gives clear contextual guidance: it is for cancelling an owned export and explicitly retains the source video, implying it is the right choice when you want to keep the source for another export. However, it does not explicitly compare to alternatives (e.g., cancel_animation) or state when not to use it, leaving some inference.

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