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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description must carry most behavioral weight; it does disclose that the model is pinned by the endpoint, which is a genuine behavioral constraint not visible as a schema property. It says nothing about the operation being long-running/asynchronous, whether a task handle or URL is returned, or how to retrieve the result (a nexscope_media_task_result sibling exists), which is a notable gap for a generation endpoint.

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, no preamble, with the input-mode scope front-loaded and the hard constraint immediately after. Every clause carries information an agent needs before calling.

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?

With 10 parameters, rich schema descriptions, and no output schema, the description covers invocation adequately but omits lifecycle information. For a video generation call, the absence of any note on result delivery, expected latency, or how the mutual-exclusion rules between image/video/lastFrameImageUrl inputs are enforced leaves an agent under-informed about what happens after the call.

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 the baseline would be 3, but the description adds a constraint the schema cannot express: videoType must not be sent even though additionalProperties is true and the property is absent from the schema. That is real value beyond the structured fields, though no other parameter (duration, resolution, aspect ratio, promptOptimizer) receives extra explanation.

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 gives a specific verb and resource ("Generate a compact Seedance 2.0 video") and enumerates the three accepted input modes (primary image, up to 9 reference images, or a reference video), which tells an agent exactly what the tool consumes. It does not distinguish this 'mini' variant from the closely named siblings nexscope_seedance_2_0_video_generation, nexscope_seedance_2_0_fast_video_generation, and nexscope_seedance_2_5_video_generation, so selection between them still requires inference.

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?

Usage is only implied through input-mode phrasing; there is no statement of when to choose this model over the standard/fast/2.5 Seedance siblings or over Kling/Wan/Hailuo generation tools. The one real directive is negative — that videoType must not be supplied because the model is fixed — which is useful but narrow.

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