Skip to main content
Glama

search_tax_tribunal_decisions

Search Korean tax tribunal decisions by tax type (customs, income, corporate, VAT) and keywords. Filter by decision dates, disposition dates, or sort results.

Instructions

[조세심판] 조세심판원 결정례 검색. 관세·소득세·법인세·부가세 등 세목별 검색 가능.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoSearch keyword (e.g., '자동차', '부가가치세')
displayYesResults per page (default: 20, max: 100)
pageYesPage number (default: 1)
clsNoDecision type code (재결구분코드)
ganaNoDictionary search (ga, na, da, etc.)
dpaYdNoDisposition date range (YYYYMMDD~YYYYMMDD, e.g., '20200101~20201231')
rslYdNoDecision date range (YYYYMMDD~YYYYMMDD, e.g., '20200101~20201231')
sortNoSort option: lasc/ldes (decision name), dasc/ddes (decision date), nasc/ndes (claim number)
apiKeyNo법제처 Open API 인증키(OC). 사용자가 제공한 경우 전달

Implementation Reference

  • Main handler function that executes the search logic. Calls the law API (lawSearch.do/ttSpecialDecc), parses XML results via parseTaxTribunalXML, and formats the response listing decisions with case name, claim number, decision date, etc.
    export async function searchTaxTribunalDecisions(
      apiClient: LawApiClient,
      args: SearchTaxTribunalDecisionsInput
    ): Promise<{ content: Array<{ type: string, text: string }>, isError?: boolean }> {
      try {
        const extraParams: Record<string, string> = {
          display: (args.display || 20).toString(),
          page: (args.page || 1).toString(),
        };
        if (args.query) extraParams.query = args.query;
        if (args.cls) extraParams.cls = args.cls;
        if (args.gana) extraParams.gana = args.gana;
        if (args.dpaYd) extraParams.dpaYd = args.dpaYd;
        if (args.rslYd) extraParams.rslYd = args.rslYd;
        if (args.sort) extraParams.sort = args.sort;
    
        const xmlText = await apiClient.fetchApi({
          endpoint: "lawSearch.do",
          target: "ttSpecialDecc",
          extraParams,
          apiKey: args.apiKey,
        });
    
        // 공통 파서 사용
        const result = parseTaxTribunalXML(xmlText);
        const totalCount = result.totalCnt;
        const currentPage = result.page;
        const deccs = result.items;
    
        if (totalCount === 0) {
          return {
            content: [{
              type: "text",
              text: "검색 결과가 없습니다."
            }]
          };
        }
    
        let output = `조세심판원 재결례 검색 결과 (총 ${totalCount}건, ${currentPage}페이지):\n\n`;
    
        for (const decc of deccs) {
          output += `[${decc.특별행정심판재결례일련번호}] ${decc.사건명}\n`;
          output += `  청구번호: ${decc.청구번호 || "N/A"}\n`;
          output += `  의결일자: ${decc.의결일자 || "N/A"}\n`;
          output += `  처분일자: ${decc.처분일자 || "N/A"}\n`;
          output += `  재결청: ${decc.재결청 || "N/A"}\n`;
          output += `  재결구분: ${decc.재결구분명 || "N/A"}\n`;
          if (decc.행정심판재결례상세링크) {
            output += `  링크: ${decc.행정심판재결례상세링크}\n`;
          }
          output += `\n`;
        }
    
        output += `\n💡 전문을 조회하려면 get_tax_tribunal_decision_text Tool을 사용하세요.\n`;
    
        return {
          content: [{
            type: "text",
            text: output
          }]
        };
      } catch (error) {
        return formatToolError(error, "search_tax_tribunal_decisions");
      }
    }
  • Zod schema defining input parameters: query (optional keyword), display (1-100 results), page, cls (decision type code), gana (dictionary search), dpaYd/rslYd (date ranges), sort (sort option), and apiKey.
    export const searchTaxTribunalDecisionsSchema = z.object({
      query: z.string().optional().describe("Search keyword (e.g., '자동차', '부가가치세')"),
      display: z.number().min(1).max(100).default(20).describe("Results per page (default: 20, max: 100)"),
      page: z.number().min(1).default(1).describe("Page number (default: 1)"),
      cls: z.string().optional().describe("Decision type code (재결구분코드)"),
      gana: z.string().optional().describe("Dictionary search (ga, na, da, etc.)"),
      dpaYd: z.string().optional().describe("Disposition date range (YYYYMMDD~YYYYMMDD, e.g., '20200101~20201231')"),
      rslYd: z.string().optional().describe("Decision date range (YYYYMMDD~YYYYMMDD, e.g., '20200101~20201231')"),
      sort: z.enum(["lasc", "ldes", "dasc", "ddes", "nasc", "ndes"]).optional()
        .describe("Sort option: lasc/ldes (decision name), dasc/ddes (decision date), nasc/ndes (claim number)"),
      apiKey: z.string().optional().describe("법제처 Open API 인증키(OC). 사용자가 제공한 경우 전달"),
    });
  • Tool registration entry linking the name 'search_tax_tribunal_decisions' to its schema and handler function.
    {
      name: "search_tax_tribunal_decisions",
      description: "[조세심판] 조세심판원 결정례 검색. 관세·소득세·법인세·부가세 등 세목별 검색 가능.",
      schema: searchTaxTribunalDecisionsSchema,
      handler: searchTaxTribunalDecisions
    },
  • Import statement that pulls the searchTaxTribunalDecisions function and its schema from the tax-tribunal-decisions.ts module.
    import { searchTaxTribunalDecisions, searchTaxTribunalDecisionsSchema, getTaxTribunalDecisionText, getTaxTribunalDecisionTextSchema } from "./tools/tax-tribunal-decisions.js"
    import { searchCustomsInterpretations, searchCustomsInterpretationsSchema, getCustomsInterpretationText, getCustomsInterpretationTextSchema } from "./tools/customs-interpretations.js"
  • Query router entry that maps Korean keywords like '조세심판' or '세금심판' to the search_tax_tribunal_decisions tool.
    {
      name: "tax_tribunal",
      patterns: [
        /조세\s*심판|세금\s*심판/,
      ],
      tool: "search_tax_tribunal_decisions",
      extract: (query) => ({
        query: query.replace(/조세심판원?|세금심판|결정례?/g, "").replace(/\s+/g, " ").trim(),
      }),
      reason: "조세심판 키워드 → 조세심판 결정례 검색",
      priority: 10,
    },
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It mentions searching by tax type but does not disclose behavioral traits such as pagination limits, rate limits, data freshness, or any side effects.

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 description is concise, consisting of two sentences. It is front-loaded with the entity in brackets and provides essential information without fluff.

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

Completeness2/5

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

Given the tool has 9 parameters, no output schema, and no annotations, the description is too minimal. It does not explain return values or provide sufficient context for effective use, though the schema covers parameter details.

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%, so the description adds no new meaning beyond the schema. The mention of searching by tax type maps loosely to the 'query' parameter but does not enhance understanding of other parameters.

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?

The description clearly states the tool searches tax tribunal decisions and lists the tax types available for search. It distinguishes itself from sibling 'get_tax_tribunal_decision_text' by focusing on search rather than retrieval of a specific decision.

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

Usage Guidelines2/5

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

The description does not provide any guidance on when to use this tool versus alternatives, nor does it mention when not to use it. It only implies usage for searching tax tribunal decisions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/workbookbulb863/korean-law-alio-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server