generate_video

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

Description adds significant behavioral details beyond annotations: de-duplication within ~20s, one clip per call, need for separate calls with different seeds for variants, and approximate render time (1-10 min). Annotations only indicate non-readonly and non-destructive; description fills the gaps.

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?

Description is concise (one paragraph) and front-loaded with the core purpose. However, it could be slightly more structured (e.g., bullet points for two modes). No wasted words.

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 11 parameters, all documented in schema, and no output schema, the description covers return format (request_id, cost) and polling mechanism. It does not explicitly mention all sibling tools but the context is sufficient for an AI agent.

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 already covers all 11 parameters with descriptions (100% coverage). The description adds value by explaining de-duplication behavior and idempotency_key usage, which is not fully captured in 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?

Clearly states the tool starts video generation from text or image, with immediate return of request_id and cost, and distinguishes between text-to-video and image-to-video modes. It differentiates from siblings like generate_image and compose_video.

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?

Provides explicit guidance on when to use text-to-video versus image-to-video (by passing image_url). Mentions polling with wait_generation as a follow-up. Does not explicitly list when not to use but implies through context.

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