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

The description goes beyond annotations by explicitly disclosing that the tool spends prepaid USDC, settles before enqueuing, and returns cost. This adds meaningful context to the destructiveHint=true annotation, clarifying the exact side effect and the payment flow. The description does not contradict any annotation; in fact, it reinforces them with concrete details.

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 is concise and well-structured, packing essential information into two sentences: the endpoint, behavior, return values, confirmation requirement, and polling alternatives. The most critical facts (spending USDC and confirmation) are front-loaded, and every sentence earns its place without redundancy.

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?

The description covers the action, side effects, and return values, but omits any explanation of the parameters, which is especially problematic given the low schema coverage and absence of an output schema. For a tool with six parameters, the description is incomplete; an agent would not know how to correctly set optional fields like duration, resolution, or aspect_ratio, nor what valid values are.

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 description provides no information about any of the six parameters. With schema description coverage at only 17% (only model has a description), the agent receives no guidance on duration, resolution, aspect_ratio, or prompt content. The description fails entirely to compensate for the schema's lack of parameter documentation, leaving the agent to guess how to populate these fields.

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 clearly states the tool generates a video via POST to /v1/video/queue, and specifies it settles then enqueues, returning queue_id and cost. It identifies itself as an 'intent tool' and mentions polling with get_generation_status or wait_for_video, giving context. However, it does not explicitly differentiate from sibling tools like video_queue, which serves a similar purpose, so it's not fully distinguished.

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 gives strong guidance to confirm before calling because it spends prepaid USDC, and instructs the agent to poll with get_generation_status or wait_for_video afterward. However, it does not state when this tool should be used instead of alternatives like video_queue, nor does it provide exclusions or conditions. The usage context is partially covered but lacks explicit decision rules.

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