제주 병의원(1,046곳)·약국(321곳)을 검색합니다. 출처: 국립중앙의료원 공공데이터. open_now=true 로 '지금 영업중'(한국시간 기준 서버 판정), day='sun' 으로 일요일 진료를 필터할 수 있습니다. 각 결과에 요일별 진료시간·전화·좌표가 포함됩니다.
| Name | Required | Description | Default |
|---|---|---|---|
| day | No | 해당 요일에 여는 곳만 (hol=공휴일) | |
| kind | No | 시설 종류 (생략 시 전체) | |
| name | No | 이름 부분 일치 (예: 온누리약국) | |
| limit | No | 최대 결과 수 (기본 10) | |
| region | No | 읍·면·동 이름 또는 '제주시'/'서귀포시' (예: 노형동, 애월읍) | |
| open_now | No | 지금 영업중만 (한국시간 기준) | |
| emergency | No | 응급의료기관만 (병원) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden. It clearly implies a read-only search operation, identifies the data source, notes that open_now is server-side judged in Korean time, and specifies that results include weekday hours, phone, and coordinates. This goes beyond the minimum for a non-destructive lookup tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three compact sentences front-load the core purpose, then explain key filters, then summarize result contents. There is no filler, and every sentence contributes useful information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, but the description compensates by stating that each result includes weekday opening hours, phone, and coordinates. It also gives the data source and filter semantics. Minor gaps remain around default behavior and combined filter logic, but the overall context is strong for a search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already documents all parameters with 100% coverage, so the baseline is 3. The description adds a little extra meaning by explaining server-side time judgment for open_now and the Sunday-filter example, but it does not substantially deepen parameter understanding beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: '제주 병의원...검색합니다' (search Jeju hospitals/clinics and pharmacies). It includes the exact counts, the data source, and the key filtering capabilities, so an agent immediately knows what the tool does and how it differs from unrelated siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear operational guidance by explaining how to use open_now and day filters, and states the data source. There are no closely related sibling tools for facility search, so no explicit exclusion of alternatives is needed; this level of contextual guidance is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource or workflow (posts, facilities, jobs, property, personas, stats), and descriptions clarify normal-user vs persona posting and feed vs keyword vs by-ID retrieval. The only mild overlap is create_post vs post_as_persona, both create posts, but the persona-specific flow is clearly documented.
Tool names follow a consistent snake_case verb_noun pattern (get_, list_, search_, create_, upsert_). Minor deviations are find_facilities instead of search_facilities and post_as_persona as a prepositional verb, but these are easy to predict.
16 tools is slightly above the typical well-scoped 3-15 range, but the breadth reflects multiple verticals (community posts, jobs, property, facilities, stats). Each tool has a role, so the count feels reasonable rather than bloated.
The set covers read/search/create for posts and upsert/search for jobs and property, plus supporting listings and stats. However, there are no update/delete operations for posts or personas, no comment tools despite comment counts being mentioned, and no delete for structured listings, leaving notable lifecycle gaps.