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

Annotations already declare readOnly=false, idempotentHint=false and openWorld=true, yet the description adds the key consequence: the same request is regenerated and re-billed every time, plus per-quality cost figures. That billing/idempotency context is genuinely useful beyond the structured hints, though it says nothing about latency or how the resulting image is delivered.

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?

Purpose and cost are front-loaded, which is good, but the per-image pricing is stated twice – once inline and again in a bracketed duplicate – which is redundant bloat.

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?

With no output schema and six mostly self-documented parameters, the description supplies the cost model, non-idempotent billing behavior and mode coverage that an agent needs before spending credits. It would be more complete if it noted whether generation is synchronous or how the image is returned.

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 every parameter (size, prompt, quality, background, output_format, reference_image_url) is already documented in the schema. The description only echoes the quality-to-price mapping already present in the quality field, adding no syntax or format detail beyond it.

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 (생성) and resource (이미지 한 장), and the explicit '한 장' (single image) scope implicitly separates it from the batch sibling image_batch_create. It stops short of naming any sibling outright, so it is clear but not maximally differentiated.

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 describes the two supported modes (text-only vs. reference-image-plus-text), which implies how to invoke it, but gives no explicit when-to-use/when-not guidance and never points to image_edit or image_batch_create as alternatives.

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