Skip to main content
Glama
Sign In

산재 신청 도우미 (sanjae-apply)

by io.github.seojaehong
OverviewDiscussionsAdmin

산업재해조사표 작성 지침(읽기 전용)

get_accident_report_guide
Read-onlyIdempotent

산업재해조사표(산업안전보건법 시행규칙 별지 제30호서식, 관할 지방고용노동관서 제출)의 제출 의무·기한(발생일부터 1개월)·근로자대표 확인·중대재해 즉시 보고·과태료(시행령 별표 35), 칸별 작성법, 서술 칸(재해발생 개요·원인·재발방지 계획)의 요소·점검표·서식 작성예시, 업종·직업 분류코드 찾는 곳, 자주 틀리는 것, 제출 경로를 근거·확인일과 함께 돌려준다. 문장은 쓰지 않는다 — 호출한 AI 가 사업장이 준 사실로 쓴다. workplace_address 를 주면 관할 관서·접수 부서·전화·팩스 찾기 결과(find_labor_office 와 같은 내용)를 labor_office_lookup 으로 붙인다. 입력을 저장하지 않는다.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_accident_report_guide"
  }
}

Input Schema

NameRequiredDescriptionDefault
sectionNo한 절만: duty·penalties·fields·narrative·codes·common_mistakes·submission·jurisdiction. 없으면 전부
constructionNo건설업 재해인가(건설 전담 부서가 있는 관서는 그 부서로 안내)
workplace_addressNo사업장 소재지(관할 관서 찾기용)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

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/closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts: content is returned as sourced facts with confirmation dates rather than prose ('문장은 쓰지 않는다'), inputs are not stored, and a labor-office lookup is appended conditionally on workplace_address. It does not describe how the 8 sections are keyed in the response.

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 the resource name and dense with useful specifics – statutory citations, deadline, penalty table – with little wasted wording. The structure is a single long run-on sentence with dash- and comma-chained clauses, which makes it harder to scan than it needs to be.

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 carries the burden of describing returns, and it does so reasonably: named content blocks (obligations, checklist, examples, codes, submission route), sourcing and confirmation dates, plus the conditional lookup attachment. It still leaves the response envelope (section keys, JSON shape) unspecified, which matters for a guide tool that returns structured facts.

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%, so all three parameters are already documented, giving a baseline of 3. The description adds real meaning beyond the schema by explaining the conditional effect of workplace_address (attachment of a find_labor_office-equivalent lookup), though it says nothing extra about the construction boolean beyond the schema text.

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 uses a concrete verb ('돌려준다') and enumerates the exact resource: the 별지 제30호서식 submission duty/deadline, penalties (시행령 별표 35), field-by-field instructions, narrative sections, code lookup, common mistakes, and submission route. The scope is unmistakable, but it never distinguishes itself from the closest sibling check_accident_report (validation) or says why an agent should choose this guide over that tool.

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?

Usage is only implied: it is clearly a reference-lookup tool, and it states that supplying workplace_address attaches a labor-office lookup. There is no explicit when-to-use/when-not guidance and no routing statement against fill_form, check_accident_report, or find_labor_office, even though the description acknowledges its output overlaps with find_labor_office.

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

All 산재 신청 도우미 (sanjae-apply) 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