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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral value beyond structured fields: it names the return value (modelId) and explains that private:true restricts to the private AI model line (i2v models).

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-loads the purpose and the returned artifact, then layers the option space efficiently. Dense but every clause maps to an actual parameter dimension, so nothing is wasted; slightly clause-heavy punctuation keeps it from a clean 5.

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 read-only, no-output-schema tool, the description covers purpose, the return artifact, and all parameter axes. It does not explain failure modes (e.g., no model matches the constraints), which is the only notable gap.

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 schema already documents all four parameters, setting a baseline of 3. The description adds meaning on top, glossing media='tool' as upscale/background removal and clarifying private:true as the private i2v model line, exceeding the baseline.

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 (decide/recommend a model) and, crucially, the output contract: returns the modelId to use with generate_image. This distinguishes it from list_models and generate_image without needing to open a schema.

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?

Enumerates the decision dimensions (cheapest/fastest/best quality, image/video/tool, with/without source image), effectively telling the agent the contexts in which it applies. It stops short of naming alternatives or when-not-to-use conditions, so it is clear context rather than full routing guidance.

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