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

Annotations already establish this is a non-readonly, non-idempotent, open-world write, so the bar is lower. The description adds genuinely useful context beyond that: generation consumes credits (a cost the agent must confirm with the user), and the finished video lands as a draft rather than being published. It implies async execution via the getVideoStatus pointer but never states that the call returns immediately.

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 with zero filler. The core action is front-loaded, followed by model selection, cost confirmation, and result tracking in the order an agent would actually need them.

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For an async generation tool with no output schema, the definition covers the important post-call reality (draft, unpublished, poll with getVideoStatus). The one gap is that it never says what the call itself returns, such as a job or video identifier that getVideoStatus would consume.

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 80%, so the schema already documents model ids, defaults, supported durations, and the aspect-ratio enum. The description adds no parameter syntax or format detail beyond what the schema provides, so the baseline of 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?

The description opens with a specific verb and resource: 'Start AI video generation from a prompt.' That is unambiguous about what the tool does, and it implicitly separates itself from publishVideo by stating the output is a draft. It does not, however, distinguish itself from the similarly named sibling createVideo, which an agent could easily confuse it with.

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 gives explicit prerequisites and routing: use listModels with kind=video to check models, supported lengths, and credit costs, confirm the model and cost with the user first, and check progress with getVideoStatus. Both the model-selection step and the progress-tracking alternative are named concretely, so nothing is left to inference.

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