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

Annotations only declare the generic shape (not read-only, open-world, non-destructive). The description adds the traits that actually matter: ~60s or longer latency, expected wait, and the billing consequence of retrying after an apparent timeout. That is exactly the beyond-annotation context an agent needs.

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?

Front-loads what the tool produces and its return value, then adds the latency warning and the anti-retry rule. Every sentence carries operational weight; nothing is 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 slow, billable, non-idempotent generation tool with no output schema, the description covers latency expectations, user-facing messaging, failure semantics, retry cost, and the return format. Nothing an agent needs to call it correctly 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 description coverage is 100% and both parameters (prompt, aspect_ratio enum) are already documented in the schema. The description adds no parameter-level detail, so the baseline 3 applies.

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) and resource (a short video with Google Veo 3 Fast), notes that audio is included, and names the concrete return value (a link to the finished video). This distinguishes it from the sibling generate_video_kling and the generate_image_* tools.

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?

Gives explicit procedural guidance: tell the user before calling that generation takes ~a minute, and do not silently retry on apparent failure. It stops short of stating when to prefer this over the sibling video/image generators, so it is clear context but not full alternative routing.

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