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

The description adds substantial behavioral context beyond the sparse annotations: it reveals the pricing model ($0.35/video) and the asynchronous execution flow (returns a generation_id, poll get_generation). This is exactly the kind of operational behavior an agent needs to know and would not infer from the schema.

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 cover purpose, cost, and async workflow with zero filler. The purpose is front-loaded and each clause earns its place, making it easy to scan.

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 tool with no output schemacompanion, the description covers the essential operational loop: it returns a generation_id and tells the caller how to wait for completion. It does not cover failure handling, format constraints, or what the final result will look like, but the schema covers inputs, and the referenced get_generation follows up.

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 already provides 100% parameter coverage with descriptions for audio, video, and consent. The description mentions audio generically but does not add any new detail about parameter format, constraints, or relationships beyond what the schema states, so the baseline of 3 is appropriate.

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?

"Sync lips to any audio" is a clear verb+resource combination that evokes the tool's function immediately. It does not explicitly distinguish from siblings like ai_talking_photo, but the phrase is specific enough that an agent can generally tell it apart.

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?

There is no guidance on when to choose this tool over alternatives or when not to use it. The only mention of another tool is get_generation for polling completion, which is a follow-up step rather than an alternative selection.

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