Skip to main content
Glama

HOTKER 핫커 | 한국 상품·휴대폰 성지 구매가 AI

by ai.hotker
OverviewDiscussionsAdmin

HOTKER 계산 근거 확인

get_calculation_evidence
Read-onlyIdempotent

HOTKER 계산 엔진 버전, 산식 설명, 통신사 출처 URL과 한계를 data.engines, data.carriers, data.limitations로 반환합니다. 계산 결과를 설명하거나 출처를 제시할 때 사용하세요. 무인증·읽기 전용이며 출처 사이트를 실시간 조회하거나 개인 계약을 검증하지 않습니다. calculationType은 요청 맥락 표시이며 현재 응답에서 다른 산식을 제거하지 않습니다. 실제 금액 계산은 calculate_mobile_tco, calculate_contract_penalty 또는 calculate_combo_discount를 사용하세요.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
carrierNo근거를 볼 통신사: SKT, KT, LGU_PLUS. 생략하면 3사 근거를 반환.
calculationTypeNo관심 계산 유형. 기본 all. 요청 맥락으로 반환하며 현재 엔진·산식 전체 구조는 유지.all

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYes성공 여부. 실행 실패는 isError=true와 공개 오류 코드로 별도 반환합니다.
dataYes계산: inputBasis, engine, result, 선택 notice. 근거: engines, carriers, limitations. 검색: dataAsOf, resultCount, items 및 적용 필터. 개별 자료의 관측일·유효기간도 확인하세요.
toolYes호출한 도구 이름.
statusYescalculated=입력 기준 계산, estimated=참고 추정, incomplete=정보 부족, reference=근거, verified=검색 공개 기준 통과, partner_presented=판매점 제시 조건 포함(통신사 확인 전). 실제 계약 보증 아님.
generatedAtYes응답 생성 ISO 시각. 원본 자료의 갱신 시각과 다릅니다.
schemaVersionYes공개 응답 데이터 계약 버전.
mcpServerVersionYesHOTKER MCP 서버 버전.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedOutput schema / properties / status / description
      Previous value: -"calculated=입력 기준 계산, estimated=참고 추정, incomplete=정보 부족, reference=근거, verified=검색 공개 기준 통과. 실제 계약 보증 아님."New value: +"calculated=입력 기준 계산, estimated=참고 추정, incomplete=정보 부족, reference=근거, verified=검색 공개 기준 통과, partner_presented=판매점 제시 조건 포함(통신사 확인 전). 실제 계약 보증 아님."
    • changedOutput schema / properties / status / enum
      Previous value: -[
-  "calculated",
-  "estimated",
-  "incomplete",
-  "reference",
-  "verified"
-]New value: +[
+  "calculated",
+  "estimated",
+  "incomplete",
+  "reference",
+  "verified",
+  "partner_presented"
+]
  2. Changed3 schema fields changed
    • addedInput schema / properties / calculationType / description
      Added value: +"관심 계산 유형. 기본 all. 요청 맥락으로 반환하며 현재 엔진·산식 전체 구조는 유지."
    • addedInput schema / properties / carrier / description
      Added value: +"근거를 볼 통신사: SKT, KT, LGU_PLUS. 생략하면 3사 근거를 반환."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "additionalProperties": {},
+      "description": "계산: inputBasis, engine, result, 선택 notice. 근거: engines, carriers, limitations. 검색: dataAsOf, resultCount, items 및 적용 필터. 개별 자료의 관측일·유효기간도 확인하세요.",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "generatedAt": {
+      "description": "응답 생성 ISO 시각. 원본 자료의 갱신 시각과 다릅니다.",
+      "type": "string"
+    },
+    "mcpServerVersion": {
+      "description": "HOTKER MCP 서버 버전.",
+      "type": "string"
+    },
+    "ok": {
+      "const": true,
+      "description": "성공 여부. 실행 실패는 isError=true와 공개 오류 코드로 별도 반환합니다.",
+      "type": "boolean"
+    },
+    "schemaVersion": {
+      "description": "공개 응답 데이터 계약 버전.",
+      "type": "string"
+    },
+    "status": {
+      "description": "calculated=입력 기준 계산, estimated=참고 추정, incomplete=정보 부족, reference=근거, verified=검색 공개 기준 통과. 실제 계약 보증 아님.",
+      "enum": [
+        "calculated",
+        "estimated",
+        "incomplete",
+        "reference",
+        "verified"
+      ],
+      "type": "string"
+    },
+    "tool": {
+      "description": "호출한 도구 이름.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "ok",
+    "schemaVersion",
+    "mcpServerVersion",
+    "tool",
+    "status",
+    "generatedAt",
+    "data"
+  ],
+  "type": "object"
+}
  3. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new context beyond them: no authentication required, it does not query source sites in real time, and it does not verify personal contracts. It also discloses that calculationType is contextual only and does not filter the returned formula structure.

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?

Front-loaded with what is returned, followed by usage, caveats, and the alternative tools. Every sentence carries information, though the caveat sentence is dense and could be split for faster scanning.

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

Completeness5/5

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

With an output schema present, return values need not be re-explained, and the description still names the top-level buckets. It covers scope, limitations, authentication, and sibling routing, leaving no gap an agent needs to call this correctly.

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

Parameters4/5

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

Schema coverage is 100% and both params are enum-documented, so the baseline is 3. The description adds real meaning on top: it clarifies that calculationType is solely request context and currently removes no other formulas from the response, preventing an agent from assuming it narrows results.

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

Purpose5/5

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

States a specific verb and resource (returns HOTKER calculation engine version, formula descriptions, carrier source URLs and limitations) and explicitly names the output buckets data.engines, data.carriers, data.limitations. It clearly distinguishes itself from the calculate_* siblings by declaring it only supplies evidence, not amounts.

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

Usage Guidelines5/5

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

Gives the triggering condition ('계산 결과를 설명하거나 출처를 제시할 때 사용하세요') and explicitly routes actual amount computation to calculate_mobile_tco, calculate_contract_penalty, or calculate_combo_discount. When-to-use and when-not-to-use are both stated.

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

All HOTKER 핫커 | 한국 상품·휴대폰 성지 구매가 AI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources