ocr_identi4Extract key fields from a Korean certified copy of resident registration (deungbon) image via OCR. 주민등록등본 사진에서 주요 정보를 추출해 구조화된 결과와 원문 텍스트(raw_text)를 반환합니다. 정보주체의 동의 등 적법한 처리 근거를 확보한 경우에만 사용하십시오. [호출당 12포인트]
| Name | Required | Description | Default |
|---|---|---|---|
| image_url | Yes | 다운로드 가능한 https URL (허용 형식: image/png, image/jpeg) (최대 50MB) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, covering the non-destructive nature. The description adds value beyond this by stating the output format (structured results and raw_text) and a per-call cost of 12 points. It also mentions the legal processing requirement, which is a precondition behavior not captured in annotations. No contradiction detected.
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 relatively short and front-loaded with the core purpose. However, it repeats the same information in English and Korean, which is redundant and slightly wasteful. The additional notes on legal basis and cost are useful but could be more compact. Still, it is efficient enough for an agent to parse quickly.
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 mentions it returns 'structured results and raw_text' but does not specify which 'key fields' are extracted. Since there is no output schema, this lack of detail limits the agent's ability to judge whether the output meets its needs. The tool is simple (one parameter) and the annotations cover safety, but the return value expectations are vague. More specifics about the fields would improve completeness.
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?
The input schema has 100% description coverage for the single parameter `image_url`, including allowed formats (png/jpeg) and size limit (50MB). The tool description does not add any additional semantic detail about the parameters beyond what the schema already provides. Baseline 3 is appropriate when the schema fully documents parameters.
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 verb 'Extract', the specific resource 'Korean certified copy of resident registration (deungbon)', and the method 'OCR'. It distinguishes itself from sibling tools by targeting a specific document type (deungbon) rather than generic OCR or other document variants. The return of 'structured results and raw_text' further clarifies its 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?
The description implies usage for deungbon images and explicitly provides a usage condition: 'Use only if you have secured lawful processing grounds such as consent from the data subject.' However, it does not explicitly compare to sibling tools (e.g., 'use ocr_identi1 for other documents'), leaving the alternative routing implicit. The legal condition adds valuable context for when it is appropriate to invoke.
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 clearly distinct purpose: the generic `ocr` handles any image, while `ocr_identi1` through `ocr_identi5` are each tied to a specific document type (resident card, driver license, passport, certified copy, alien card). There is no ambiguity about which tool to use for a given input.
All tools follow a consistent `ocr` prefix with snake_case, and the specific ones use `ocr_identi` + numeric suffix. While the pattern is predictable, the numeric suffixes are not descriptive of the document type, which reduces self-documentation slightly.
Six tools is well-scoped for an OCR server. The generic tool handles broad use cases, and the five specific tools cover common identity documents without redundancy or bloat.
The server provides both a general OCR tool and structured extraction for the most common Korean ID documents. There are no obvious dead ends; the domain is fully covered for typical OCR and identity-document needs.