identity_document_passportExtract key fields from a passport image and mask the passport number and MRZ area. 여권 인적사항면 이미지에서 지정 정보를 추출하고 여권번호 및 MRZ 영역을 마스킹한 이미지를 함께 반환합니다. MRZ 2줄이 포함되도록 촬영한 PNG 또는 JPEG 이미지 파일 하나만 전달하면 되며, 마스킹된 이미지는 JSON 응답의 masked_image 필드에 base64로 포함됩니다. 정보주체의 동의 등 적법한 처리 근거를 확보한 경우에만 사용하십시오. [호출당 30포인트]
| Name | Required | Description | Default |
|---|---|---|---|
| image_url | Yes | 다운로드 가능한 https URL (허용 형식: image/jpeg, image/png) (최대 50MB) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description adds valuable behavioral context: it returns a masked image in a base64 'masked_image' field, notes the point cost, and emphasizes legal compliance. No contradiction with annotations; the description enriches the operational understanding.
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 yet informative, using both English and Korean. It front-loads the core purpose, then covers input requirements, output format, legal notice, and cost. Every sentence contributes value without 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?
Given a single parameter with complete schema coverage and no output schema, the description explains the input format, the specific output field (masked_image base64), and the legal/constraint context. It could mention which key fields are extracted, but this is not critical for invoking the tool correctly.
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 covers 100% of the parameter (image_url with format and size limits). The description adds meaningful extra guidance: the image must be captured so that both MRZ lines are included, which is not in the schema. This helps the agent select an appropriate image URL.
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?
States a specific verb-resource pair ('Extract key fields from a passport image and mask the passport number and MRZ area') that precisely distinguishes this tool from siblings like driver's license or ID card tools. The bilingual description reinforces the passport-specific scope.
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?
Gives clear usage context: operates on the passport information page image, requires MRZ 2 lines to be included, and specifies PNG/JPEG format. It also states a legal precondition (consent basis). While it doesn't explicitly name alternative tools, the passport-specific wording makes the appropriate scenario obvious.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct purpose: masking (hide_rrn), text-based verification (identi_cardN), image-based verification (identi_card_imageN), extraction with masking (identity_document_*), and name/RRN matching (name_rrn_auth). Within each group, the document type is clearly specified, so there is no ambiguity between tools.
Naming follows clear patterns: identi_card* for verification (with _image for image-based), identity_document_* for extraction, and descriptive names like hide_rrn and name_rrn_auth. While the prefixes differ across functional groups, each group is internally consistent and the names are readable and predictable.
16 tools is on the higher end but appropriate for the server's scope, covering five document types with two verification modes (text and image), four extraction/masking tools, a generic masking tool, and a name/RRN auth check. Each tool fills a needed role, though the number is slightly elevated due to the text/image split.
The server covers the core operations for identity document verification and extraction across all major Korean ID types. A minor gap is the lack of an extraction/masking tool for the resident registration certificate (identi_card4), but this is not a critical omission given the existing verification and masking capabilities.