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

korean-tax-calc-mcp

personal_deduction

Read-onlyIdempotent

Computes Korean global income tax personal deductions—basic and additional (senior, disabled, single parent, female household head)—from taxpayer and dependent data.

Instructions

Personal deduction for global income tax: basic and additional (인적공제). 종합소득 인적공제(기본공제·추가공제). 언제: 종합소득세 신고에서 기본공제·추가공제 금액을 구할 때. 입력: 귀속연도 → year, 납세자 정보 → taxpayer, 부양가족 목록 → persons. 결과: 기본공제·추가공제·인적공제·사람별 내역·근거. 기본공제 1인당 150만원, 추가공제(경로우대 100만·장애인 200만·부녀자 50만·한부모 100만).

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": {
      "year": "<year>",
      "taxpayer": "<taxpayer>",
      "persons": "<persons>"
    },
    "name": "personal_deduction"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearYes사업연도·귀속연도(2016~2026)
personsYes[{name, relation, birth_year, income_items?, income?, wage_only_gross?, disabled?, cohabiting?}] — name: 사람 표시 이름(문자열, 중복 불가). relation: 공제대상자와의 관계. 허용값: 배우자·직계존속·직계비속·입양자·형제자매·수급자·위탁아동. 문항 표현 그대로 '아들'·'딸'·'자녀'는 '직계비속', '부친'·'모친'·'부모'는 '직계존속'으로 적을 것. birth_year: 출생연도(정수, 나이 계산용). income_items: [{kind, amount}] — 부양가족 소득 종류·금액 목록. kind 허용값: 근로_총급여·사업소득금액·이자·배당·공적연금·사적연금·기타소득금액·양도소득금액·퇴직소득금액·전통주_제조소득_농어촌·비과세·공적연금_과세제외. income_items를 쓰면 income·wage_only_gross는 함께 입력할 수 없음. disabled: 장애인 여부(bool). cohabiting: 동거 여부(bool, 기본 True, 형제자매·수급자는 동거 필요). 소득 없음 → income_items: []. 근로소득만 있음 → income_items: [{"kind": "근로_총급여", "amount": 총급여}]. 예시: [{"name":"부친","relation":"직계존속","birth_year":1938,"income_items":[{"kind":"공적연금_과세제외","amount":30000000}]}]
taxpayerYes{sex, birth_year, has_spouse, comprehensive_income, disabled?, household_head?} — sex: '남'|'여'. birth_year: 출생연도(정수). has_spouse: 배우자 유무(bool). comprehensive_income: 종합소득금액(원, 기본공제 한도 판단용). disabled: 장애인 여부(bool, 기본 무시). household_head: 세대주 여부(bool, 부녀자 공제 판단용).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.21.0
    • changedInput schema / properties / persons / description
      Previous value: -"[{name, relation, birth_year, income_items?, income?, wage_only_gross?, disabled?, cohabiting?}] — name: 사람 표시 이름(문자열, 중복 불가). relation: 공제대상자와의 관계. 허용값: 배우자·직계존속·직계비속·입양자·형제자매·수급자·위탁아동. 문항 표현 그대로 '아들'·'딸'·'자녀'는 '직계비속', '부친'·'모친'·'부모'는 '직계존속'으로 적을 것. birth_year: 출생연도(정수, 나이 계산용). income_items: [{kind, amount}] — 부양가족 소득 종류·금액 목록. kind 허용값: 근로_총급여·사업소득금액·이자·배당·공적연금·사적연금·기타소득금액·양도소득금액·퇴직소득금액·전통주_제조소득_농어촌·비과세·공적연금_과세제외. income_items를 쓰면 income·wage_only_gross는 함께 입력할 수 없음. disabled: 장애인 여부(bool). cohabiting: 동거 여부(bool, 기본 True, 형제자매·수급자는 동거 필요). 소득 없음 → income_items: []. 근로소득만 있음 → income_items: [{\"kind\": \"근로_총급여\", \"amount\": 총급여}]. 예시: [{\"name\":\"부친\",\"relation\":\"부친\",\"birth_year\":1938,\"income_items\":[{\"kind\":\"공적연금_과세제외\",\"amount\":30000000}]}]"New value: +"[{name, relation, birth_year, income_items?, income?, wage_only_gross?, disabled?, cohabiting?}] — name: 사람 표시 이름(문자열, 중복 불가). relation: 공제대상자와의 관계. 허용값: 배우자·직계존속·직계비속·입양자·형제자매·수급자·위탁아동. 문항 표현 그대로 '아들'·'딸'·'자녀'는 '직계비속', '부친'·'모친'·'부모'는 '직계존속'으로 적을 것. birth_year: 출생연도(정수, 나이 계산용). income_items: [{kind, amount}] — 부양가족 소득 종류·금액 목록. kind 허용값: 근로_총급여·사업소득금액·이자·배당·공적연금·사적연금·기타소득금액·양도소득금액·퇴직소득금액·전통주_제조소득_농어촌·비과세·공적연금_과세제외. income_items를 쓰면 income·wage_only_gross는 함께 입력할 수 없음. disabled: 장애인 여부(bool). cohabiting: 동거 여부(bool, 기본 True, 형제자매·수급자는 동거 필요). 소득 없음 → income_items: []. 근로소득만 있음 → income_items: [{\"kind\": \"근로_총급여\", \"amount\": 총급여}]. 예시: [{\"name\":\"부친\",\"relation\":\"직계존속\",\"birth_year\":1938,\"income_items\":[{\"kind\":\"공적연금_과세제외\",\"amount\":30000000}]}]"
  2. Addedv0.12.2

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. What the description adds is the shape of the return (기본공제·추가공제·인적공제·사람별 내역·근거), which is genuinely useful given there is no output schema. It does not discuss edge-case behavior (e.g. what happens when a dependent fails the income or cohabitation test), so credit beyond annotations is moderate.

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 definition is well front-loaded with labeled sections (언제/입력/결과) so an agent can scan trigger, arguments, and output in order. The cost is duplication: every line appears in both English and Korean, and the statutory amounts are repeated in the closing sentence. Efficient in content, slightly wasteful in form.

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?

For a three-parameter, nested-object tool with no output schema, the description supplies what the structured fields cannot: the return contents (per-person breakdown plus 근거/grounds) and the statutory rates needed to sanity-check results. Combined with 100%-covered parameter descriptions and full annotations, an agent has everything required to call it correctly and interpret the response.

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 description coverage is 100% and the nested persons/taxpayer descriptions already enumerate allowed relation values, income kinds, mutual exclusion of income_items vs income, and a worked example. The description's '입력' line merely restates the parameter mapping (귀속연도 → year, 납세자 정보 → taxpayer, 부양가족 목록 → persons). Per the coverage rule, baseline 3 is correct; the description adds no syntax or constraint detail beyond the schema.

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 a specific resource and computation — personal deductions (basic and additional, 인적공제) for global income tax — and even enumerates the sub-components (기본공제 1인당 150만원, 경로우대 100만·장애인 200만·부녀자 50만·한부모 100만). An agent can tell this is the per-person deduction calculator rather than a general deduction or tax-credit tool. It stops short of naming a sibling to contrast against, so a 4 rather than 5.

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' line explicitly states the trigger context: when obtaining basic/additional deduction amounts during a comprehensive income tax filing. That is a clear use condition rather than an implied one. No exclusion conditions or alternative tools are mentioned, which keeps it at 4.

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