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

Annotations declare destructive/openWorld/non-idempotent, and the description adds non-redundant operational facts: it is async, returns a jobId to be polled via get_job, and SPENDS CREDITS. Cost and the async lifecycle are genuinely useful and not captured by the annotations, though no auth or failure behavior is given.

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?

Front-loaded with the highest-stakes facts first (what it does, ASYNC + poll target, SPENDS CREDITS), then progressive detail on references. Every clause adds distinct information with no filler.

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 7-param async generation tool with no output schema, the description covers the job lifecycle, cost, and the complex reference parameter. Minor gaps remain: no guidance on typical latency or on choosing among the video-generating siblings.

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?

With only 14% schema coverage the description carries the burden, and it does for the hardest parameter: it explains reference counts, the {source,id} vs {url,mediaType} shapes, the @Image/@Video/@Audio token behavior, and the audio ≤15s + generateAudio=true coupling. Model/duration/resolution/aspectRatio are left to the schema, but those enums are largely self-describing.

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+resource ('Generate a video with BytePlus Seedance 2.0') and immediately distinguishes its scope with the ASYNC jobId/return pattern. An agent can tell it apart from studio_generate_video and create_video by the SeedDance engine and multimodal-reference capability.

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?

Gives a concrete pre-step ('call optimize_seedance_prompt first for best results') and routes reference input to list_seedance_library / list_seedance_actors. It does not, however, say when to choose this over the sibling video tools (studio_generate_video, create_video), so there is no explicit exclusion.

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