Generate Video

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

With no annotations provided, the description carries the full burden. It discloses the async nature, processing time, and that it polls automatically, as well as dependencies like ffmpeg for thumbnails. It also implies mutations (creating files) but without explicit warnings, but this is covered by the nature of generation. It adds value beyond the schema by explaining behavior like automatic polling.

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 relatively compact for a complex tool, with key information front-loaded (model, duration, inputs, audio), followed by a warning about async processing. It uses bullet points effectively. It could be more concise, but for the complexity it is well-structured and not verbose.

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 high schema coverage and descriptive schema (nested objects, enums, bounds), the description completes the picture by explaining output artifacts (file path, thumbnail, HTML player) and processing time. It does not explain return structure, but there's no output schema, and the description hints at what is returned. For a generation tool with no output schema, this is adequate.

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 schema already has 100% coverage with detailed descriptions for each parameter, including example prompts, resolution trade-offs, and image input alternatives. The description reinforces the overall purpose but does not add additional parameter-level semantics beyond what's in the schema. Since coverage is high, a baseline of 3 is appropriate, but the description's mention of output paths and thumbnail/HTML player adds slight context, hence a 4.

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 that it generates videos using Google Veo 3.1, with specific details on duration, input types (text prompt, first-frame image, reference images), audio generation, and output artifacts (video file, thumbnail, HTML player). It distinguishes it from sibling image tools by emphasizing video generation and asynchronous processing.

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?

It explains key usage context: asynchronous with 2-5 minute processing time, automatic polling, and supports optional inputs like first-frame and reference images. It does not explicitly mention when NOT to use it or alternatives, but the context is clear enough for an agent to decide, especially with sibling tools like generate_image.

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