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

Annotations say only readOnly=false, openWorld=true, destructive=false; the description supplies the traits that actually matter here – ~60s latency, per-duration credit pricing (60/90/120), audio included, and the retry-causes-rebilling hazard. That is exactly the beyond-annotations context an agent needs before a slow, paid, non-idempotent call.

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 is produced, then cost, then latency, then the pre-call and failure-handling instructions. Every sentence carries actionable information – no filler and no repetition of schema fields.

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?

No output schema, but the description states the return value (a video link). Combined with latency, pricing, audio and the retry hazard, an agent has everything needed to call this correctly and set user expectations.

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 goes further by tying duration to explicit credit costs (4s=60, 6s=90, 8s=120), which the schema's duration enum does not convey. Aspect ratio is still left entirely to the schema, so it is not a full 5.

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 (video) plus the exact model (Google Veo 3.1 Fast) and the output ('link to the finished video'). An agent can distinguish it from generate_video_kling and the generate_image_* siblings by the named model and the fact it produces audio.

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 clear operative context: warn the user first, expect ~60s, do not silently retry on timeout because it may double-bill. It does not explicitly compare against the sibling generate_video_kling (cheaper/faster? different model quality?), so the alternative-selection guidance is incomplete.

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