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

Adds substantial behavioral context beyond annotations: ASYNC jobId flow, credit consumption, multimodal reference constraints (≤9 images, ≤3 videos, ≤3 audio clips), token-citation mechanics, and audio duration/lipsync requirements. This is exactly the kind of non-obvious behavior an agent needs to know.

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?

Dense but well-organized; every sentence carries actionable information. The async and credit warnings are front-loaded, followed by the optimization tip and reference mechanics. Slightly long, but all content earns its place.

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 complex async, credit-consuming video generation tool with no output schema, the description covers the jobId return, polling path, reference construction, audio constraints, and generateAudio guidance. An agent has enough to call correctly and interpret the response.

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 only 14%, so the description must compensate. It does for the most complex parameter (references), explaining both library-row and URL formats, pairing rules, and token placement. It does not explain model, duration, resolution, or aspectRatio, but those are simpler enums/ranges where the schema is sufficient.

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: 'Generate a video with Seedance 2.0 / 2.5'. It distinguishes itself from sibling `seedance_generate_image` by naming the output modality and model family, and the async jobId behavior separates it from other video tools.

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?

Provides clear workflow context: async, poll get_job, and an explicit tip to call optimize_seedance_prompt first. It does not enumerate alternatives or say when this tool is preferable to studio_generate_video/create_video, but the workflow guidance is concrete and useful.

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