Extend Video

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

Annotations already mark the call as non-read-only and non-destructive; the description adds that local paths are rejected before any HTTP call, which is useful fail-fast behavior. It does not discuss job asynchrony or side effects, but the annotations lower the burden and the added validation context is meaningful.

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?

A single dense sentence front-loads the action and then packs in the endpoint, payload shape, and the key input constraint. No filler or redundant elaboration.

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?

With an output schema present and all parameters described in the schema, the description supplies the essential extra context: the endpoint and pre-HTTP validation behavior. A note on whether the call returns a job id asynchronously would be a nice addition, but the tool is still sufficiently complete.

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 description coverage is 100%, so the schema already fully documents model, source, prompt, and duration. The description mostly restates the source semantics and gives the HTTP endpoint, adding little new parameter meaning beyond what the schema provides.

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 opening phrase 'Extend a finished video' names a specific verb and resource, and the POST endpoint with payload makes the operation unambiguous. It is clearly distinguishable from sibling tools like create_video or get_video_status.

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?

'Finished video' states the prerequisite, and the source restriction to a job id or https URL with local paths rejected tells the agent which inputs are valid. It does not explicitly name an alternative tool for non-extension generation, so it stops just short of full routing guidance.

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