Skip to main content
Glama

get_support_departments

Retrieve staffing counts for support departments by position and grade. Filter by department, position, or grade to analyze workforce distribution.

Instructions

업무지원 부서별 직위·직급 인원 현황 조회 (10,015건).

부서명, 직위명, 직급명, 인원수를 제공한다. 조직 내 인력 배분 및 직무 구조 파악에 활용.

※ 전체 조회 시 최대 200건 반환. 필터 사용 권장.

dept_name: 부서명 부분일치 필터 (예: "서울역", "AI전략본부", "차량사업소") position: 직위명 부분일치 필터 (예: "역장", "팀장", "기술원") grade: 직급명 부분일치 필터 (예: "사무영업3급", "운전4급", "토목5급")

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gradeNo
positionNo
dept_nameNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Install Server

TDQS

A4.3/5.0
Behavior4/5

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

Despite no annotations, the description discloses key behavior: returns at most 200 rows on a full query, recommends filters, and clarifies that filters are partial matches (부분일치) with examples. The verb '조회' implies a read operation, so there is no concern about side effects. However, it omits details like pagination, error behavior, or whether the result set is sorted, so it carries less than the full burden.

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

Conciseness5/5

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

The description is compact, with a clear opening, a purpose sentence, a warning about the 200-row limit, and a bullet-style parameter guide. No redundant sentences; each part adds value, and the most critical constraint (limit) is highlighted early.

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?

Given an output schema is present, explaining return values isn't needed. The description covers purpose, usage, filter mechanics, and a limit. Minor gaps such as default ordering or handling of empty results are not critical for an agent to call the tool correctly.

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

Parameters5/5

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

All three parameters are documented in the description with meaning (부서명, 직위명, 직급명) and examples of partial-match values. Since the input schema lists only names and defaults, the description fully compensates for the 0% schema coverage, giving agents precise guidance on what to pass.

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 the verb '조회' (inquiry) and specifies the resource: headcount statistics by department, position, and grade. It lists the returned fields (부서명, 직위명, 직급명, 인원수) and the use case, making the tool's purpose unambiguous. It does not explicitly contrast with sibling tools like get_job_grades or get_homepage_position, but the resource is distinct enough.

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?

It provides clear context: states the tool is for analyzing workforce allocation and job structure, and explicitly advises using filters because a full query returns at most 200 records. This is practical guidance, but it does not name alternative tools or state when not to use this tool, so it stops short of a full 5.

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

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/lovelyquality/korail-mcp'

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