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

Annotations indicate readOnlyHint false, so the tool is write/mutation-oriented. The description adds significant behavioral context: async execution (30-90s), background delivery to library, and returns a task_id per shot. It doesn't explicitly state it is destructive or requires specific permissions, but given the richness of the schema and narrative, it provides good transparency beyond annotations.

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?

The description is dense but front-loaded with the most important actions (call list_video_models, pass one shot or shots for storyboard). It is efficient, though slightly long due to coverage of many model-specific details. Every sentence adds value, but could be tightened by moving model-specific duration details to the schema.

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?

Given the tool's high complexity (20 parameters, many conditionally required, multiple model-specific behaviors), the description together with the schema is remarkably complete. It covers prerequisites, async behavior, polling, shot constraints, and essential edge cases (face reference verification, audio track ignored in reference videos). No output schema exists, but the description explains the return value (task_id per shot) adequately.

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 the description enriches many parameters beyond the schema: for example, it explains that shots must be distinct, that duration has model-specific behavior (e.g., auto bills 30s cap upfront), that face_reference_ids require server-side verification, and that video_edit/upscale source can be a job id or URL. This goes well 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?

The description clearly states the tool generates Switch video across multiple real providers and modes. It specifies the exact providers (Kling, Seedance, etc.) and modes (text-to-video, image-to-video, etc.), distinguishing it from sibling tools which are either for analysis, style application, audio, or asset management.

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 description explicitly instructs the agent to call list_video_models first to pick the right model and mode. It provides clear guidance on how to construct shots (one shot or a storyboard with max 4 by default, hard max 10, each distinct) and notes async behavior with polling via get_video_status or list_my_videos. This differentiates usage from siblings and gives actionable prerequisites.

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