Generate a video

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

Beyond the annotations (openWorld=true, idempotent=false, destructive=false), it discloses real behavior: the payload is priced first with a free quote, calls are refused locally above CARPE_MAX_PER_CALL_USD, and the call returns a job_id for asynchronous completion taking minutes. It omits the consent-refusal flow (NEEDS_CONSENT) and any rate-limit detail, but the cost/budget and async semantics are the operationally important parts.

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?

Three dense sentences, front-loaded with the action and capability set, followed by cost behavior and the async follow-up path. The model-name list (Sora, Veo, Kling, Seedance, Wan, LTX, Grok Imagine) is slightly padded but signals coverage breadth usefully.

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 16-parameter, nested-object, asynchronous mutation with no output schema, the description covers the essentials an agent needs: what gets created, that it costs money and can be refused, what is returned (job_id), and how to finish the job. Remaining gaps are per-field semantics, which the schema partially covers.

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 56%, so several parameters (resolution, aspect_ratio, end_image_url, negative_prompt, reference_* arrays, extra, route) are undocumented in both places. The description partially compensates by pointing to carpe_model_details for valid durations/aspect ratios/resolutions and by framing the payload as priced, but it adds no syntax or meaning for the remaining undocumented 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?

States a specific verb and resource ('Queue a video') plus the modalities it covers (text-to-video, image-to-video, reference-to-video) and example models. It is clearly distinguishable from the sibling carpe_video_status (which downloads) and carpe_model_details (which lists constraints).

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 the agent: poll/download with carpe_video_status once ready, and read durations/aspect ratios/resolutions with carpe_model_details before calling. It does not state exclusions (e.g., use carpe_image_generate for stills), so the alternative-selection guidance is clear but not exhaustive.

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