Generate a video

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

Annotations are absent, so the description carries the full burden. It discloses the 1-5 minute duration, the possibility of returning a task id instead of a final result, and the support for both text-to-video and image-to-video. This is critical behavioral information beyond what the schema provides. There is no contradiction with annotations since none exist.

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, no filler. The purpose and models are front-loaded, followed by the crucial async behavior and the reference_images hint. Every phrase earns its place, and the structure guides the agent from what it does to how to handle its long-running nature.

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 6 parameters and no output schema, this description is remarkably complete. It covers the async behavior, the task-id fallback, and the two generation modes. It does not detail when to pick each model, but the model enum descriptions in the schema cover that. Nothing an agent needs to correctly invoke the tool 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. The description adds value by linking reference_images to image-to-video and noting that tier affects pricing (even though that is in the schema description, the description reinforces it). It also clarifies that a size matching no tier falls back to the base rate. These enrichments justify a score above baseline.

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?

States a specific verb ('Generate') with a clear resource ('a video'), and names the available models (Veo 3.1, Grok Imagine, Omni Flash). It distinguishes from the sibling generate_image by the output type, and implicitly from check_job by mentioning the async task-id return. The scope is unambiguous.

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 clear context on when to use the tool (for video generation) and explicitly explains the long-running nature and the fallback to check_job if it exceeds the wait budget. It does not explicitly state when not to use it, but the async behavior and the mention of check_job effectively guide the agent on how to handle the response. Lacks an explicit alternative like 'use generate_image for still images', but that is obvious from the names.

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