Skip to main content
Glama

얼굴 유사도 비교

face_similarity
Read-only

Compare the main face in a reference image with the face in another image and return a 0-1 similarity score, a match decision and a level (high/medium/low). Use it to check an ID card photo against a selfie. 기준 사진과 비교 사진의 대표 얼굴이 같은 사람인지 0~1 점수와 판정(is_match)으로 알려줍니다. 신분증 사진과 셀피 대조에 씁니다. [호출당 10포인트]

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "image_url": "<image_url>",
      "compare_image_url": "<compare_image_url>"
    },
    "name": "face_similarity"
  }
}

Input Schema

NameRequiredDescriptionDefault
image_urlYes다운로드 가능한 https URL (허용 형식: image/jpeg, image/png, image/webp, image/bmp) (최대 50MB)
thresholdNo같은 사람으로 판정할 기준 점수 (범위: 0.2 ~ 0.8, 기본값 0.4, 높을수록 엄격)
compare_image_urlYes다운로드 가능한 https URL (허용 형식: image/jpeg, image/png, image/webp, image/bmp) (최대 50MB)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the exact return contents (0-1 score, match decision, high/medium/low level) and a per-call cost of 10 points, which is a real quota constraint an agent should budget for. It omits failure behavior such as what happens when no face is detected or a URL is unreachable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core capability and return values are front-loaded in the first sentence, and the cost note is a compact bracketed tag at the end. The only waste is full bilingual duplication, where the Korean sentences restate the English almost verbatim; acceptable for a bilingual API but not maximally tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly takes on the burden of explaining returns (score, is_match, level) and adds cost, which is what an agent needs before calling. The remaining gap is edge-case behavior (undownloadable URL, no detectable face), which matters for a two-URL remote-fetch tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both image URLs and the threshold (range, default 0.4, directionality) fully documented in the schema. The description mentions the score and match decision but adds no syntax, format, or interaction detail for the three parameters beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource ('compare the main face in a reference image with the face in another image') and names the output shape, which implicitly separates it from generic siblings like image_similarity or face_detection. It never names those siblings explicitly, so an agent must infer the boundary rather than being told.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives one concrete scenario ('check an ID card photo against a selfie') which anchors intent well. However there is no when-not guidance, no prerequisite about faces being present in the images, and no routing advice toward image_similarity for non-face comparisons, leaving selection partly to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.