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

Annotations declare the safety profile (openWorld, non-idempotent, non-destructive), but the description adds non-obvious behavior annotations cannot express: generation is asynchronous, the result lands as an unpublished draft, and cost confirmation is required up front. The unpredictability of cost is a real behavioral caveat that is disclosed.

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?

Four short sentences, all front-loaded: action, prerequisite, approval gate, follow-up. No restatement of the name or filler, and the draft-not-published caveat sits where an agent will read it before calling.

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?

Covers the full lifecycle (validate model → confirm cost → generate → poll with getVideoStatus) with no output schema to compensate for. It stops short of saying what the call returns immediately (a job/video id presumably), which an agent must assume to use getVideoStatus.

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?

At 80% schema coverage the baseline is 3; the description adds meaning to model and duration by pointing at listModels for valid lengths and per-model credit pricing, which the schema only partially encodes. The one uncovered parameter, contentGroupId, is never explained in either place, keeping it off a 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?

"Start AI video generation from a prompt" gives a specific verb (start/generate) plus resource (video) and signals an asynchronous job, which cleanly separates it from sibling upload/publish tools like createVideo and publishVideo. An agent can tell it apart from generateImage and createVideo without opening either schema.

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?

Explicitly routes to listModels with kind=video to discover models, supported lengths and credit costs, mandates confirming model and cost with the user first, and names getVideoStatus for progress. Both the prerequisite step and the follow-up tool are stated rather than inferred.

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