Put a character into your own video

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

Annotations only declare the safe-mutation profile (readOnly=false, destructive=false, openWorld=true). The description adds substantial behavioral context beyond that: cost model (3 credits/second, rounded up, capped at 30s), several-minute render time, background execution, a visible 'AI generated' label burned into output, and file size/duration limits. These are exactly the facts an agent needs before invoking.

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 paragraph that is well front-loaded: the operation and its visual semantics come first, then requirements, then cost, then the polling workflow. It is long, and the CLI alias and the schema-duplicated mp4/50MB/30s constraints are slightly redundant, but every sentence carries operational value.

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 still covers the return value (clip id and status), the asynchronous nature of the call, and the complete completion-detection loop. For a 4-parameter, asynchronous, credit-consuming generation tool, nothing material 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 baseline is 3, but the description adds meaning beyond the schema: 'image' must be a designed character look rather than a user photo, and 'driver' is a local file that gets uploaded first. keep_sound and resolution are left to the schema, which already documents them adequately.

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 ('put an AI influencer into a video... the character takes the place of the person in it') with explicit scope constraints and a direct mapping to the CLI equivalent `clipugc videos replace`. It is clearly distinguishable from siblings like create_motion_clip or merge_ad, which involve different operations.

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?

Explicitly states prerequisites (a character look designed in ClipUGC, not the user's own photo; a local mp4/mov file), the upload-first requirement, and the exact follow-up workflow (poll get_video every 5-10s, then download_video). It also routes credit checks to get_credits. This is about as complete as usage guidance gets.

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