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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description adds useful operational context: the accepted MIME types (image/jpeg, image/png), the maximum size (50MB), the base64 response format, the cost, and a legal-use warning. It could further disclose error behaviors (e.g., invalid image handling), but the description clearly exceeds the annotations' minimal signal.

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 with the key purpose, then the operational details, legal note, and cost. Every sentence contributes: input type, output location, legal condition, and pricing. No redundancy.

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 one-parameter tool with a 100%-covered schema and read-only annotation, the description conveys the purpose, input constraints, output location, legal usage condition, and cost. It lacks explicit notes on failure/error cases or what '지정 정보' (specified fields) means exactly, but the core call flow is sufficiently documented.

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 value by clarifying that only one image file is needed, that the URL must be downloadable via HTTPS, the allowed formats, and the size limit. It does not repeat the schema's property name but confirms the expected usage flow.

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 ('Extract key fields from a Korean driver license image') and a concrete resource (Korean driver license), plus the distinctive masking behavior. It is clearly distinguishable from sibling tools like identity_document_id_card / passport / residence_card because it names the document type and its masking target (RRN last 6 digits).

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 explicitly states the input requirement ('PNG 또는 JPEG 이미지 파일 하나만 전달'), the output location ('masked_image 필드에 base64로 포함'), the legal precondition ('정보주체의 동의 등 적법한 처리 근거를 확보한 경우에만 사용'), and the cost ('호출당 30포인트'). It distinguishes this tool from generic OCR or other identity document tools by the masking behavior and document type.

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