wan_generate_video_from_image

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

With no annotations, the description must carry behavioral disclosure. It does mention that the tool returns a Task ID and video information including URLs and state, and it hints at async behavior via the 'callback_url' parameter. However, it does not explain polling workflows, typical generation times, timeout implications, or failure modes—gaps for a long-running generation tool.

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 front-loaded with a clear first sentence, followed by a structured list of models and a return value line. It is appropriately sized for the tool's complexity, though the model list slightly duplicates the schema's model enum, preventing a perfect score.

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 return value format and model choices, and an output schema exists to handle structured return data. It falls short on explicitly guiding the user through the asynchronous nature and when to use this versus sibling tools, but it still provides enough context for a generation task with a rich schema.

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 covers 100% of the 14 parameters with descriptive text, so the description does not need to repeat parameter semantics. It adds value by explaining model options, but this does not go beyond what the schema already provides for individual parameters.

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 first sentence uses a specific verb ('Generate') and resource ('AI video from a reference image'), immediately clarifying the tool's core function. It also explicitly names 'Wan image-to-video models' and lists three distinct model variants, which differentiates it from the sibling 'wan_generate_video' (likely text-to-video).

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 provides clear context by listing the three model options with their intended use cases (standard, reference-video, fast). However, it does not explicitly state when to choose this tool over 'wan_generate_video' or other siblings, leaving that exclusion implicit.

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