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

Annotations only declare non-read-only, open-world, non-destructive; the description goes well beyond by disclosing the credit cost model (scaled by clip length), the hard input constraints (MP4, 15s, 50MB), and the asynchronous contract (returns task_id, poll get_video). These are exactly the facts an agent needs before committing to a paid, long-running call.

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 sentences, front-loaded with the operation and its hard limits, then the cost and async contract. Every clause carries operational information—no restatement of the name or title.

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 no output schema, the description correctly covers the return path (task_id then get_video) and supplies the cost and size limits an agent would otherwise lack. Nothing needed to invoke this correctly is missing.

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 explains prompt, video_url and the image 1/image 2 reference convention for image_urls. The description's mention of 'the person from a photo' loosely reinforces image_urls but adds no constraint or syntax the schema doesn't already supply, so the 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?

Specific verb + resource (edit an existing video clip), plus the input format, duration and size envelope, and the exact class of edits supported (outfit, style, background, scene) while preserving motion and timing. An agent can distinguish this from create_video or animate_photo 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?

It makes clear this operates on an existing clip with instructions and explicitly routes the agent to get_video for polling the result. It does not, however, contrast this with create_video or animate_photo as alternatives for non-editing generation, so the when-not branch is left implicit.

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