Put your AI influencer into your own video

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), the description discloses credit cost per second with a cap, background/asynchronous generation, multi-minute render latency, the visible "AI generated" label burned into the output, and upload behavior. That is far richer than annotations alone.

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?

Purpose is front-loaded, followed by requirements, cost, and the polling workflow in a logical order with no filler. It is a dense block of text rather than cleanly separated sentences, which slightly hurts scannability, but every clause carries useful information.

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 compensates by stating the return value (clip id and status), that generation is asynchronous, and the exact polling loop (get_video with {"id": <clip id>, "kind": "clip"} every 5-10s until completed/failed) followed by download_video. Nothing an agent needs to complete the workflow 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 coverage is 100%, so the parameters are already documented. The description reinforces the image and driver semantics (influencer look vs. user photo, mp4/mov limits) but adds little syntax beyond the schema, and keep_sound and resolution are only covered by the schema. 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?

States a specific verb and resource: an AI influencer takes the place of the person in the user's own video, preserving the original room, light and camera. This is clearly distinguishable from sibling tools like create_clip, create_motion_clip and create_character, which do not perform person replacement on an existing clip.

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?

Gives concrete preconditions (a ClipUGC-designed influencer look, not the user's own photo; a local mp4/mov under 50 MB and 30s) and an explicit cost-check step via get_credits. It does not directly contrast with sibling generation tools, but the prerequisites are specific enough to route the agent correctly.

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