start_image_edit

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

Annotations already indicate the tool is non-read-only and non-destructive; the description adds that the operation runs through generate_image and that the result is captured. It does not disclose whether originals are modified, how outputs are persisted, or error behavior, but the annotation safety profile covers the most critical ambiguity.

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?

One tight sentence with no filler; it states the action, scope, and mechanism immediately. The description is short but purposeful, with the most important distinguishing information front-loaded.

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 nine parameters, no output schema, and thin annotations, the description needs to cover prerequisites, return/capture behavior, and defaults, but it provides only a high-level operation. It leaves an agent unsure of how the result is returned or saved and what the unconstrained parameters mean.

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 only 44%, so the description should compensate for undocumented parameters. It does not explain effort, max_retries, output_name, aspect_ratio, or timeout_minutes; the only parameter-related content ('one to five') merely restates the schema's min/max items. That is insufficient for a 9-parameter tool.

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 names a specific operation ('Edit or transform'), a resource ('reference images'), and the mechanism ('Antigravity's native generate_image tool'). It also bounds the resource count to one to five, which distinguishes this from pure generation tools.

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 'explicitly supplied reference images' signals the key context: this tool is for editing existing images, not generating from scratch. It stops short of explicitly naming alternatives or exclusions, but the required image_paths parameter makes the intended use reasonably clear.

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