generate_video

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

With no annotations, the description carries full burden. It discloses download destination (kie/assets/raw/), explains async behavior via wait parameter, polling with check_task/download_result, and download_dir semantics. It also mentions the polling budget default and that Sora 2 is paused. This is thorough behavioral disclosure.

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 lengthy but well-structured with a MODEL GUIDE section and notes. It is front-loaded with the core purpose and each sentence earns its place. While some redundancy exists (e.g., repeated 'NEW' markers), it remains efficient given the complexity. A slight trim could improve, but currently it's well-organized.

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?

Given 9 parameters, no output schema, and complex model selection, the description is remarkably complete. It covers model choice, async mode, file handling, polling settings, and even upstream issues (Sora 2 paused). It also references sibling tools for extension. The agent has all necessary context to invoke the tool correctly.

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 100%, so baseline is 3. However, the description adds significant value: model guide explains usage of model parameter, wait parameter async mode, download_dir absolute path requirement, and model_options for model-specific settings. It also clarifies max_wait_seconds defaults. This far exceeds 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 clearly states 'Generate a video using kie.ai (86+ models). Downloads to kie/assets/raw/.' It specifies the verb (generate), resource (video), and provider. The detailed model guide with use-case recommendations distinguishes it from sibling tools like generate_image or generate_music.

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 extensive guidance: MODEL GUIDE with model recommendations for cinematic, fast, budget, avatar, etc. It explicitly mentions when to use image-to-video, avatar models, and extend tools. It also notes alternatives like veo_extend and suggests using list_models to explore. This fully addresses when and when not to use the tool.

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