Generate video

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

Discloses asynchronous job creation, cost tier, and no-billing for failures. These details go beyond annotations (readOnlyHint, openWorldHint) to inform agent behavior.

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?

Three sentences, front-loaded with core action, no extraneous information. Efficiently conveys all critical points.

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?

Covers async polling, cost, and failure billing. Given the output schema exists, return values are not needed. Provides sufficient context for an agent to use the tool correctly.

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 input schema includes descriptions for all parameters, so baseline is 3. The description adds context for prompt and image_url but does not elaborate on duration_s, preference, or aspect_ratio. Schema coverage is reported as 60%, but actual schema text shows full descriptions, so the description adds only marginal value.

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 clearly states the tool's purpose: generating a video from a text prompt, with optional source image animation. It distinguishes itself from sibling tools like generate_image and get_job by mentioning asynchronous behavior and cost comparison.

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: use get_job to poll for completion, cost comparison with images helps choose between tools, and failed generations are not billed. Lacks explicit when-not-to-use scenarios but covers main usage.

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