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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description carries most of the burden. It usefully discloses that the model is pinned and that videoType must be omitted — a real behavioral rule not encoded in the schema (additionalProperties is true). It says nothing about the async nature of video generation, expected latency, or how results are retrieved (a nexscope_media_task_result sibling exists), which is a substantial omission for a long-running generation call.

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?

Two sentences, front-loaded with the operation and the input modes, then the hard constraint. Nothing is padded and every clause carries information.

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?

Ten parameters at full schema coverage and no output schema is handled adequately by the schema itself. What's missing is the operation-level context an agent needs before calling: whether the call blocks or returns a task handle, roughly how long it takes, and how to fetch the finished video — all material for a video-generation endpoint.

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%, including conflictsWith constraints and enum lists, so the schema already does the param work and the baseline is 3. The description restates the input-mode alternatives and the 30-image cap, marginally reinforcing mutual exclusivity but adding no syntax, default, or interaction detail beyond what the schema provides.

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 Seedance 2.5 video") plus the three supported input modes, so the operation is unambiguous. It does not differentiate itself from the many sibling generators (seedance_2_0_video_generation, seedance_2_0_fast, kling, wan, hailuo), leaving the agent to infer when 2.5 is preferred.

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?

Enumerating the three input modes (primary image, up to 30 reference images, reference video) implicitly tells the agent how to drive the tool, and the explicit ban on videoType prevents a common error. However, there is no guidance on when to choose this model over the 2.0/fast/mini siblings or over competing video models, and no prerequisite or cost/timing expectations.

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