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

The description adds substantial behavioral context beyond the annotations: immediate point deduction (장수×25포인트 선차감), instant refund for failed images, no cancellation after submission, and per-image pricing. It also confirms the async nature of the operation. Nothing contradicts the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) — the cost and no-cancellation policy are exactly the kind of disclosure that annotations don't capture.

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 with zero waste: the first states the core function and scope, the second covers cost/refund/cancellation policy, and the third states pricing. Information is front-loaded with the primary purpose first, and every sentence earns its place.

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 9-parameter, no-output-schema submission tool, the description covers the essential operational aspects: what it does, cost, refunds, cancellation, and async behavior. The main gap is that it doesn't state what the response contains (e.g., a batch/task ID) or how to track completion, though the async framing and sibling names image_batch_status and image_batch_result make this inferable.

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 semantic context beyond the schema: it binds image_count to the cost formula (장수×25포인트), explains mode covers both generate and edit, and clarifies the async behavior of the whole operation. This goes beyond what the schema's brief field descriptions provide, though it doesn't enumerate individual parameter details.

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 states a specific verb (접수합니다 - accepts/submits), resource (이미지 대량 작업 - bulk image tasks), and scope (1~50 images, async, generate or edit). It clearly differentiates from the single-image siblings image_generate and image_edit by emphasizing the batch and asynchronous nature, so an agent can tell them apart without opening the schema.

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 context through '1~50장의 비동기 생성 또는 편집 작업' (bulk, async, 1-50 images), which signals when to prefer this over single-image tools, and the async wording implies pairing with image_batch_status/image_batch_result. However, it never explicitly names alternatives, states conditions for choosing this tool, or says when not to use it.

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