generate_image

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

No annotations are provided, so the description carries the full burden. It does disclose two important behaviors: the tool returns the generated image and saves it to disk, and it identifies the model provider. However, it does not specify where the image is saved, what output format to expect, or whether any system state changes beyond the file save occur.

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 a single, efficient sentence. The core action is front-loaded ('Generate a new image from a text description'), followed by the key side effect and return behavior. Every clause contributes meaningful 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?

For a tool with no output schema and no annotations, the description is adequate but incomplete. It conveys the essential action and result, but leaves gaps such as the save location/filename, whether an API key or model configuration is required, and how it relates operationally to the sibling edit_image tool. These gaps add uncertainty when an agent decides whether this is the right tool and what consequences invocation will have.

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?

The input schema already documents all three parameters with 100% coverage, so the description does not need to carry much parameter weight. The description adds only a loose connection between 'text description' and the prompt parameter, and 'Gemini AI' with the model concept, but no parameter-specific guidance beyond the schema.

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 a specific action — 'Generate a new image from a text description' — and names the provider ('Gemini AI'). This distinguishes it from siblings like edit_image, continue_editing, and generate_openai_image, so an agent can immediately understand what the tool does.

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 phrase 'new image from a text description' implies this is for generation rather than editing or continuing, and the mention of 'Gemini AI' distinguishes it from OpenAI-based siblings. However, the description does not explicitly state when to use this tool over alternatives, nor does it mention prerequisites or exclusions.

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