Skip to main content
Glama
korean-tax-calc-mcp

korean-tax-calc-mcp

extract_relations

Read-onlyIdempotent

Extract relationship tables (people, family, stakes, officers) from shareholder, family, and officer PDFs into structured draft data for tax audit or kinship verification review.

Instructions

Relationship table extraction from shareholder, family and officer PDF documents (관계표 추출). 주주명부·가족관계·임원명단 PDF에서 관계표(people/family/stakes/officers)를 추출한다. 언제: 세무조사·의료법인 친족확인 등에서 PDF 문서에 있는 관계표를 도구 입력으로 정리할 때. 입력: PDF 파일 경로 → pdf_path. 결과: people·family·stakes·officers 추출 결과(초안) + AI 생성 표시(필요 시). related_judge에 넣기 전에 사람이 확인한다. UPSTAGE_API_KEY 없이도 pypdf 로컬 추출 후 정리 가능(기본), 키 설정 시 Document Parse + Solar Pro 4로 더 정교한 표 추출. 주주명부·가족관계·임원명단 PDF에서 관계표를 뽑는다.

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": {
      "pdf_path": "<pdf_path>"
    },
    "name": "extract_relations"
  }
}

Input Schema

NameRequiredDescriptionDefault
pdf_pathYesPDF 파일 경로

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real value beyond them: results are drafts with an AI-generation marker, human verification is required before feeding related_judge, and behavior differs depending on whether UPSTAGE_API_KEY is set (local pypdf by default vs Document Parse + Solar Pro 4). It does not mention failure modes such as malformed or scanned PDFs, which keeps it from a 5.

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

Conciseness3/5

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

The purpose is front-loaded and the structure (when/input/result) is readable, but content is duplicated across the English opening and the closing Korean sentence, and the shareholder/family/officer document list appears twice. Roughly a quarter of the text could be removed without loss.

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?

For a single-parameter, read-only extraction tool with no output schema, the description covers purpose, trigger context, input, and the shape of the return value (people/family/stakes/officers drafts plus AI marker) plus the API-key dependency. What is missing is guidance on document quality or extraction failure, which for this complexity is a minor gap.

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?

Only one parameter exists and the schema already documents it ('PDF 파일 경로') at 100% coverage, so the description's '입력: PDF 파일 경로 → pdf_path' is essentially a restatement. No additional semantics (path format, remote URL, page-range) are added, making the baseline 3 correct.

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?

The description names the specific verb (extract) and resource (relationship tables: people/family/stakes/officers) and the document types it works on, so the agent can tell it is a document-extraction tool rather than one of the tax-calculation siblings. It is clear but does not explicitly contrast itself with any alternative, and the final sentence restates the same purpose.

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

Usage Guidelines4/5

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

The '언제' clause gives a concrete occasion (tax audit, medical-corporation kinship verification) where a PDF's relationship table must be converted into tool input, and it positions itself upstream of related_judge with a human check. It lacks explicit when-not-to-use or an alternative extraction path, so it falls short of a 5.

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

Deploy Server

Other Tools