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

Beyond the annotations, which only contain false hints, the description discloses the multi-minute latency, the synchronous wait behavior, the mp4 link on success, and the generation-id fallback. This is meaningful behavioral context for an expensive, asynchronous video-generation 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?

Two sentences, front-loaded with the core action and followed by the critical timing and response behavior. There is no filler, redundancy, or unnecessary 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?

For a six-parameter write-style tool with no output schema, the description covers the essential invocation context: what it generates, how long it takes, what it returns in each outcome, and where to poll for completion. It does not address error cases or credit requirements, so it is not perfect.

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 input schema already documents 100% of the parameters with useful descriptions, so the description does not need to repeat them. It adds no extra semantics for model, duration, aspect ratio, or reference images beyond what the schema provides, which keeps this at baseline.

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 concrete verb phrase, 'Generates an AI video from a prompt (or from an image)', identifying both the resource and the two main input modes. It is clear as a video-generation tool, though it does not explicitly distinguish itself from adjacent siblings such as fattly_generate_ad_video or fattly_animate_photo.

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 clear operational context by explaining the expected runtime, the ~2-minute wait, and the fallback to fattly_video_status when rendering is not finished. It does not enumerate when to prefer this tool over other video-related siblings, but the prompt/image-to-video use case is implied strongly enough.

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