face_detectionDetect faces in an image and return their coordinates. 이미지 파일에서 얼굴을 인식해 해당 좌표를 반환합니다. use_feature=1 입력 시 얼굴 특징 정보를 함께 반환합니다. [호출당 3포인트]
| Name | Required | Description | Default |
|---|---|---|---|
| image_url | Yes | 다운로드 가능한 https URL (허용 형식: image/jpeg, image/png, image/webp, image/bmp) (최대 50MB) | |
| threshold | No | 얼굴 추출 민감도 (범위: 0 ~ 0.9, 기본값 0.5, 높을수록 정확한 얼굴만 추출) | |
| use_feature | No | 얼굴 특징 정보 포함 여부 (포함: 1, 미포함: 0, 기본값 0) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations include readOnlyHint=true, and the description is consistent with that by describing a read-only detection operation. It adds value beyond annotations by disclosing the per-call cost (3 points) and the behavior of use_feature=1. However, it does not cover error handling or output format, which is acceptable given the annotation coverage.
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 repeats the core message in both English and Korean, which is redundant and adds length. It also appends a cost note, making it longer than necessary. While the first English sentence is front-loaded, the overall structure is not concise.
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 states that coordinates are returned but does not specify the format (e.g., bounding boxes). It also does not describe how the threshold parameter affects results, though the schema covers that. Given there is no output schema, the lack of output format details is a notable gap. Overall, the tool is adequately described but not fully complete.
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 descriptions for all three parameters (image_url, threshold, use_feature) with 100% coverage, so the baseline is 3. The description only redundantly mentions use_feature, which does not add new meaning beyond the schema. No additional parameter semantics are provided.
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 'Detect faces in an image and return their coordinates,' identifying a specific verb and resource. It also mentions the optional feature return. However, it does not explicitly name or differentiate from sibling tools like face_blur, so it stops short of a perfect score.
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 no guidance on when to use this tool versus alternatives such as face_blur or nsfw_detection. It only explains what the tool does and notes a cost, with no exclusions or conditions for selecting it.
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.