edit_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 only states the editing action and models, but does not disclose whether the original image is modified or preserved, where the output is saved, what the return format is, or any model-specific limitations. The presence of an outputDir parameter in the schema suggests file saving, but this is not mentioned in the description.

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, clear sentence with no wasted words. It is appropriately front-loaded with the essential purpose. However, it is arguably too sparse given the tool's complexity, but as a concise summary it remains effective.

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?

The tool has 7 parameters and no output schema or annotations, so the description should compensate. It does not explain return values, output file behavior, the mutual exclusivity of imageData and imagePath, or provide guidance on selecting between the two models. The description is incomplete for an agent to fully understand the tool's behavior without additional inference from the schema.

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 all 7 parameters. The description does not add additional meaning beyond naming the models; it does not clarify prerequisites like the requirement of either imageData or imagePath, nor does it explain the meaning of resolution or aspectRatio beyond the enums. Baseline of 3 is appropriate.

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 edits an existing image using specific Gemini models (Nano Banana 2 or Nano Banana Pro). It distinguishes itself from sibling tools like generate_image (which creates new images) and multi_image_edit (which suggests multiple images). The verb 'Edit' + resource 'existing image' is specific and unambiguous.

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 description implies usage when you want to edit an existing image, but it does not provide explicit guidance on when to choose this tool over alternatives or mention any exclusions. It lacks context such as 'for single-image edits, use this; for multi-image, use multi_image_edit'.

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