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 and does so well. It discloses pricing per second, audio always included, model constraints (4K not available for lite), resolution/duration dependencies, the async behavior via the wait parameter, and that generate_audio is ignored on Gemini API. It does not cover error handling or return format, but the provided details exceed the minimum.

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 uses compact bullet points and clear grouping (Supports, Models, Pricing), making it easy to scan. It is longer than average but every section earns its place—especially pricing, which helps select the right model. No filler or redundancy, though it could be trimmed slightly by folding pricing into the model list.

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 14 parameters, no annotations, and no output schema, the description covers the essential decision points: modes, models, pricing, constraints, and async options. It does not describe the return value or error scenarios, but the schema covers parameter details, and the description compensates for the lack of annotations. A near-complete picture for a complex tool.

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 already covers all 14 parameters with descriptions, so the baseline is 3. The description adds meaningful value beyond the schema: pricing differences inform model selection, constraints like '1080p/4K require duration_seconds: 8' and 'Max 3 asset images or 1 style image' are highlighted, and the note about audio always being generated adds practical semantics that the schema omits.

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 opens with a specific verb+resource: 'Generate a video using Google Veo 3.1 API.' It clearly distinguishes from sibling tools (extend_video, interpolate_frames, get_video_status) by focusing on creation from text or image. The supported modes are explicitly listed, leaving no ambiguity about the tool's core function.

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 provides rich context about models, pricing, and supported input types, but it does not explicitly state when to use this tool vs. the sibling tools (e.g., extend_video, interpolate_frames). No exclusionary guidance is given, so the agent must infer from the name and scope that this is for new video generation only.

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