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

The description adds useful behavioral context beyond the annotations: it states the output is a new image, clarifies that the reference image is only reference material, and discloses the cost of 25 points per image. This complements the annotations readOnlyHint=false and idempotentHint=true without contradicting them.

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 compact and front-loaded: the first sentence states the core function, the second clarifies the reference-image behavior, and the third gives cost. The only minor redundancy is repeating the 25-point cost in brackets after already stating it in prose.

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 description covers the key operational details: single image generation, reference image purpose, new-image output, and cost. It relies on the schema for parameter details, which is appropriate given 100% schema coverage. It does not describe the return payload, but the output-schema absence is partially mitigated by the clear statement that a new image is produced.

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 meaningful semantics for reference_image_url by explaining that it is used to understand product, person, color, and composition, and that the result is a newly created image. It also clarifies that the prompt can be used alone or with a reference image.

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 action ('generate one image') and the resource, explicitly noting 'one image' (한 장) to distinguish from the batch sibling. It also explains that the result is a new image, which differentiates it from an editing operation like image_edit.

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 gives clear usage context: text alone or reference image plus text, and describes the reference image's role. However, it does not explicitly mention when not to use this tool or name alternatives such as image_edit or image_batch_create, so it stops short of full routing guidance.

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