ocr_identi3Extract key fields from a passport image via OCR. 여권 사진에서 이름, 여권번호, 발급일자, 만료일자, 생년월일 등 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?
The readOnlyHint annotation already signals a read-only operation, so the description adds value by specifying the return format (structured result and raw_text) and the cost (12 points per call). It also discloses the legal requirement. These are behavioral traits beyond the annotation. It does not contradict the annotation; the operation is an extraction, which is read-only. The description could add more about failure behavior (e.g., invalid image) but given the readOnlyHint, this is a solid 4.
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 concise, with the primary purpose front-loaded. The Korean sentence largely duplicates the English one, creating minor redundancy, but it also contributes the legal note and cost. It stays within two sentences and avoids bloat, though a more integrated single-language description could be tighter.
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 tool is simple (1 param, no output schema), so the description must convey what is returned. It does: structured result and raw_text, plus the specific fields to extract. It also mentions the legal basis requirement. It does not specify the exact shape of the structured result, but with no output schema and a clear list of fields, it is sufficiently complete for an agent to understand what it will get. The lack of an explicit output schema is compensated by the field listing.
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 schema provides 100% coverage for the only parameter (image_url) with format and size constraints, so the description does not need to add much. While the description references 'passport image', it does not elaborate on the parameter beyond what the schema already states. With full schema coverage, a baseline of 3 is appropriate; the description adds no extra semantic value here.
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 a specific verb ('Extract') and resource ('passport image via OCR'), and lists the fields to extract (name, passport number, issue/expiry dates, birth date). However, it does not differentiate itself from sibling tools like 'identity_document_passport' or the other 'ocr_identi' variants, so the agent cannot easily distinguish which tool is the right one among similar options.
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 provides a legal constraint: use only when there is a legitimate basis (consent), but it gives no guidance on when to prefer this tool over alternatives or when not to use it. There is no mention of which sibling tool to use for other document types or any condition that would exclude this tool. The legal note is a requirement, not a usage guideline for tool selection.
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.
Most tools have clearly distinct purposes; even within families like identi_card1-5 vs identi_card_image1-5, the text-input vs image-input distinction is clear. However, the sheer number of tools and some near-synonyms (e.g., ocr_identi1 vs identi_card_image1) could cause occasional misselection, but descriptions mitigate this.
Naming follows a loose verb-first pattern (check_, crawl_, download_, draw_, etc.) but includes significant deviations: bare nouns (bank_code, location, whois), numbered variants (identi_card1, identi_card_image1), and mixed prefixes (ocr_, identity_, etc.). The inconsistency is noticeable but still readable and predictable within functional clusters.
80 tools is far above the typical 3-15, but the server is a broad API aggregator covering many independent domains (banking, ID verification, media conversion, search, LLM, etc.), so the high count is somewhat justified. Still, the sheer number makes the toolkit feel unwieldy and hard to navigate, placing it at the high end of acceptable.
Within its stated purpose as a general-purpose utility API, the toolset covers a wide array of common task families: identity document verification (text and image), OCR field extraction, media conversion, web/search, domain/IP lookup, and LLM chat. Most operations have both get and act variants (e.g., set/get watermark, parcel_tracking/auto), with few obvious dead ends for typical use cases.