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

Annotations already cover read-only, idempotent, non-destructive behavior. The description adds relevant context beyond that: it returns the site's in-house prompt text and does not create a project or consume credits, though it does not elaborate on the exact return format beyond 'prompt text.'

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 front-loaded with what the tool returns, followed by intended use and side-effect exclusions. It is appropriately sized and every sentence adds practical 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?

With annotations covering safety and schema covering all parameters, the description supplies the remaining necessary context: return value is prompt text, it is for use with an external image model, and it has no project or credit side effects. Nothing critical is missing for correct invocation.

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%, so the schema already documents vehicleId, description, and style. The description reinforces vehicle and description usage but does not add meaning beyond the schema, and the optional style parameter is not discussed.

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 states a specific verb and resource: return the same Nano Banana prompt text the site sends to its in-house image generator, filled in for the chosen vehicle and description. It also distinguishes itself from generation/project-creation siblings by saying it does not create a project and does not use site credits.

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?

It gives clear intended usage: 'Use it with your own image model,' and rules out project creation and credit use. It does not explicitly name alternatives, but the exclusions effectively steer the agent away from create_project_from_image and generate_with_credits.

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