Create lipsync

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

Beyond the annotations (mutation, open-world), the description discloses crucial behavioral traits: default model selection (sync-3), project creation/reuse behavior, the requirement to poll generate_get-generation for results, and the instruction to copy signed output URLs exactly. Existing project attachment is clarified. No contradictions with annotations found.

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?

Though long, every sentence adds vital decision-making information and is front-loaded with purpose. The structure flows logically from inputs to project attachment, to script handling, to media sourcing, to return handling and alternatives. No filler or redundant statements.

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?

Given the tool's complexity (16 params, nested objects, output schema), the description fully covers all major decision points and operational steps. It explains how to supply media, how to handle user-uploaded files, how to poll for results, and when to delegate to sibling tools. The presence of an output schema reduces the need to detail return values, but the description still covers the generation id and polling flow.

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?

Even with 100% schema coverage, the description significantly enriches parameter understanding by explaining the relationships and conditional use of audioUrl/videoUrl/imageUrl vs. asset IDs vs. file objects, the exactly-one-visual/driver constraint, and the projectName default. It also clarifies that model should only be set on explicit user request, which goes beyond schema descriptions.

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 description opens with 'Create a lipsync video from audio + EITHER a video or a still image,' clearly stating the tool's specific function and resource. It distinguishes itself from siblings like tts_create and generate_create-generation by focusing on lipsync creation and pointing to generate_create-generation for advanced options.

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?

The description provides extensive usage guidance: use script+voiceId for 'make this say X' instead of calling tts_create first, prefer upload-media for chat-uploaded files, use open-upload-widget for local files, and delegate advanced needs to generate_create-generation. It also explains when to use URLs versus asset IDs versus direct file params.

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