Generate a video

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

Annotations are all false (readOnlyHint false, destructiveHint false, etc.), so the description carries the burden of behavioral disclosure. It covers the wait time (up to 10 min), automatic credit refund on failure, cost implications, and the return format (link to mp4). This goes beyond the annotations and provides useful context, though it doesn't detail edge cases like timeout behavior.

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 three sentences with no waste. It leads with the core action, then the critical cost/wait warning, and ends with the refund policy. Every sentence earns its place and is front-loaded.

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?

With 5 parameters, no output schema, and all annotations false, the description covers the key behavioral aspects (wait, cost, refund, return link) and parameter prerequisites. It doesn't explain the output structure beyond a link, but since there is no output schema, that is acceptable. The only minor gap is not describing any potential error handling beyond refunds.

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 100%, giving a baseline of 3. The description adds meaningful context for the inputImageUrl parameter (must be a fal URL and how to obtain one) and reinforces model cost implications. While the schema already lists model examples, the description ties them to pricing via fattly_list_models, adding value.

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 an AI video from a prompt or start image, distinguishing it from siblings like generate_image, generate_audio, and upload_image. The verb 'generates' plus the resource 'AI video' is specific and unambiguous.

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 explicitly warns that video is the most expensive operation and instructs the agent to confirm model and cost with the user first, which is strong usage guidance. It also notes the waiting behavior and links to fattly_list_models for pricing, though it doesn't explicitly contrast with alternatives beyond that.

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