generate_video

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

With no annotations to lean on, the description discloses several behavioral traits: it polls until done, returns URLs valid for 7 days, may take a few minutes, and carries specific cost implications. It stops short of describing failure modes, rate limits, or authentication requirements, but the core behavior an agent needs to know is covered.

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?

The description is three sentences with every sentence earning its place: the first defines the function, the second covers behavior and duration, and the third adds cost guidance. Key information is front-loaded and there is no filler.

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 schema, the description adequately explains return format (video URL(s)) and longevity (7 days). It covers the long-running nature and cost considerations. It could add error/edge-case behavior, but the schema already documents model name failures, so this is a minor gap.

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, but the description adds extra value by explaining cost behavior and pointing to a specific model value (veo-3.1-fast-fhd) as the cheapest option. It also reinforces the prompt/image relationship, going slightly beyond what the schema states.

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 primary action ('Generate a video') and the input modality ('from a text prompt (and optional reference image)'), making the resource and scope unmistakable. It differentiates itself from sibling tools like generate_image and text_to_speech by the video resource and by noting it is the most expensive modality.

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 gives clear context for use: it polls until done, may take minutes, and is the most expensive modality, which helps an agent decide whether video generation is appropriate. It does not explicitly name sibling alternatives or provide when-not-to-use rules, but the context is strong enough to guide a reasonable selection.

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