Generate an 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 of behavioral disclosure. It usefully reveals that the tool usually completes within the tool-call budget and returns the image inline, and that reference_images enables editing/reference guidance. However, it does not explain what to do when the generation does not finish inline (e.g., whether to poll check_job), nor does it cover failure modes or cost implications, which is a meaningful gap for a generation tool.

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?

Three sentences, each carrying distinct information: model choices, runtime behavior and return format, and the reference-image capability. There is no filler or redundancy, and the core purpose is front-loaded in the first sentence.

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 5-parameter tool with no output schema and full schema documentation, the description provides enough to call it correctly: which models are available, what reference_images does, and how the result is returned. The 'usually' caveat is left dangling—it does not explicitly point to check_job as the fallback for slow generations, which is a notable omission given that sibling exists. Still, the core invocation path is well covered.

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 coverage is 100%, so the baseline is 3. The description adds genuine value by naming the model options in plain language ('Nano Banana Pro/2 or GPT Image 2') and clarifying the purpose of reference_images as a mechanism for editing and reference-guided generation—something the schema's terse description only hints at. Size and tier remain adequately documented by the schema itself.

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 verb ('Generate'), a concrete resource (an image), and the exact model family ('Nano Banana Pro/2 or GPT Image 2'), making it immediately identifiable. It also states the tool supports image editing and reference-guided generation, distinguishing it from sibling tools like generate_video and check_job.

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 provides no explicit guidance on when to choose this tool over its siblings. It does not say 'use generate_video for videos' or 'use check_job to track jobs,' and the only implicit hint is 'Usually finishes within the tool-call budget,' which is too vague to serve as routing guidance. The agent is left to infer usage context from the sibling names alone.

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