gemini_start_image_edit_tool

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

No annotations are provided, so the description carries full burden. It explains the basic start behavior but fails to disclose session lifecycle (e.g., that sessions need to be ended with gemini_end_image_edit_tool), or any other side effects like cost, rate limits, or what the return object contains. This is a significant gap.

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 three sentences, directly addresses the purpose, and adds no fluff. It is well-structured and front-loaded with the core action.

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?

While the output schema exists (reducing need to describe return values), the description omits crucial workflow details like ending the session or that the session persists across calls. It does mention the continuation tool, but not the full lifecycle. Given the multi-turn nature, more context would be helpful.

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 schema already covers all parameters (100% coverage). The description adds meaningful context for file_path: 'Without file_path, Gemini generates a new image from the prompt,' which clarifies the conditional behavior. This goes beyond the schema's description.

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's purpose: 'Start a multi-turn image editing session.' It also explains the distinction between providing an existing image versus generating from prompt, and explicitly names the continuation tool, distinguishing it from siblings like gemini_generate_image_tool.

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 instructs to use gemini_continue_image_edit_tool for further edits, providing an explicit alternative. It also describes when to use without file_path, giving clear usage context for both modes of operation.

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