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

Annotations only say readOnlyHint=false and openWorldHint=true, so the description carries the rest. It usefully warns that the model is fixed and that videoType must not be sent — meaningful because the schema allows additionalProperties, so an agent could otherwise inject that field and break the call. It omits that generation is long-running and requires polling a separate task-result tool, which keeps it from a 5.

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 short sentences, zero filler. The capability statement comes first and the hard constraint ('videoType must not be supplied') is placed immediately after, so the most failure-prone rule is front-loaded.

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 an 11-parameter, paid, long-running generation tool with no output schema, the description should mention that results are delivered asynchronously and retrieved via nexscope_media_task_result. The mode and conflict picture is complete, but the post-call lifecycle an agent needs is missing.

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% and all 11 parameters carry detailed descriptions plus conflictsWith constraints, so the schema does the heavy lifting. The description only summarizes the mode exclusivity that the schema already encodes via conflictsWith, adding little parameter-level detail of its own — baseline 3 applies.

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 Wan 3 video') and enumerates the three input modes (image references, first/final frames, reference video), which lets an agent distinguish it from wan_2_6 or kling siblings by model name. It does not explicitly say how it differs from the other model-specific video tools beyond the model label, so it stops short of a 5.

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 mode list implies when the tool is applicable, and the 'videoType must not be supplied' line is a real usage constraint. However, there is no guidance on choosing this over the many sibling video generators (wan_2_6, kling_3_omni, seedance_2_5, minimax_h3) or on the async result path, leaving selection largely to inference.

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