Skip to main content
Glama

This Weekend (이번 주말)

물어서 행사 찾기

ask_events
Read-onlyIdempotent

[이번 주말: 축제·공연·전시 찾기] 한 문장으로 물으면(예: 이번 주말 부산 불꽃축제, 来週の土曜日 ソウル 展示, free concerts in Seoul on 2026-11-07) 그 말에서 날짜, 지역, 찾는 낱말을 읽어 행사를 찾습니다. 한국어, 영어, 일본어, 중국어로 물을 수 있습니다. 사이트 채팅과 같은 규칙과 뜻 검색으로 읽고 모델은 부르지 않으며, 어떻게 읽었는지 read에 적습니다. 날짜가 없으면 오늘부터 이번 주말까지 찾고, 그 사이에 없으면 60일 안에서 찾습니다. "다음 주는?"처럼 이어 묻는 질문은 앞 질문을 previous에 넣으면 빠진 주제, 지역, 날짜를 거기서 가져옵니다. 날짜와 지역을 이미 알면 search_events가 더 정확합니다.

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": {
      "question": "<question>"
    },
    "name": "ask_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo한 번에 받을 최대 개수. 1부터 20까지이고 기본값은 10입니다.
previousNo같은 대화에서 앞서 물은 질문들. 오래된 것부터 3개까지 넣습니다. 이번 질문에 없는 주제, 지역, 날짜는 그 말을 한 가장 최근 질문에서 가져옵니다.
questionYes묻고 싶은 말 한 문장(200자 이하). 날짜는 이번 주말, 11월 3일, 2026-11-07처럼 씁니다.

Output Schema

NameRequiredDescriptionDefault
noteYes넓혀 찾았거나 답하지 못한 까닭을 한 문장으로 적습니다. 없으면 null입니다.
readYes질문을 어떻게 읽었는지입니다.
limitYes
rangeYes찾은 날짜 범위(한국 시간). 읽은 날짜가 없으면 null입니다.
totalYes질문에 맞는 행사 수. 가까운 순으로 고른 후보에서 세므로 최대 40입니다.
eventsYes
coverageYes모아 둔 자료의 날짜 범위와 마지막 수집 시각. stale이 true면 저장소 대신 예비 사본에서 읽은 자료입니다.
questionYes
returnedYes
elsewhereYes물은 지역에는 맞는 행사가 없고 다른 곳에는 있을 때만 붙습니다. places는 가까운 시·도부터 그곳 행사 수(count)를, total은 전국 행사 수를 적습니다. 아니면 null입니다.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedOutput schema / properties / events / items / properties / tags / items / enum
      Previous value: -[
      -  "kids",
      -  "family",
      -  "teens",
      -  "adults",
      -  "seniors",
      -  "pets",
      -  "indoor",
      -  "outdoor",
      -  "watch",
      -  "hands-on",
      -  "food",
      -  "market",
      -  "walk",
      -  "learn",
      -  "heritage",
      -  "nature",
      -  "science",
      -  "lights",
      -  "fireworks",
      -  "books",
      -  "seasonal",
      -  "halloween",
      -  "christmas",
      -  "year-end",
      -  "new-year",
      -  "evening",
      -  "free",
      -  "partly-paid",
      -  "paid",
      -  "book-ahead",
      -  "walk-in"
      -]New value: +[
      +  "kids",
      +  "family",
      +  "teens",
      +  "adults",
      +  "seniors",
      +  "pets",
      +  "indoor",
      +  "outdoor",
      +  "watch",
      +  "hands-on",
      +  "food",
      +  "market",
      +  "walk",
      +  "run",
      +  "learn",
      +  "heritage",
      +  "nature",
      +  "science",
      +  "lights",
      +  "fireworks",
      +  "books",
      +  "seasonal",
      +  "halloween",
      +  "christmas",
      +  "year-end",
      +  "new-year",
      +  "evening",
      +  "free",
      +  "partly-paid",
      +  "paid",
      +  "book-ahead",
      +  "walk-in"
      +]
    • changedOutput schema / properties / read / properties / refusedTags / items / enum
      Previous value: -[
      -  "kids",
      -  "family",
      -  "teens",
      -  "adults",
      -  "seniors",
      -  "pets",
      -  "indoor",
      -  "outdoor",
      -  "watch",
      -  "hands-on",
      -  "food",
      -  "market",
      -  "walk",
      -  "learn",
      -  "heritage",
      -  "nature",
      -  "science",
      -  "lights",
      -  "fireworks",
      -  "books",
      -  "seasonal",
      -  "halloween",
      -  "christmas",
      -  "year-end",
      -  "new-year",
      -  "evening",
      -  "free",
      -  "partly-paid",
      -  "paid",
      -  "book-ahead",
      -  "walk-in"
      -]New value: +[
      +  "kids",
      +  "family",
      +  "teens",
      +  "adults",
      +  "seniors",
      +  "pets",
      +  "indoor",
      +  "outdoor",
      +  "watch",
      +  "hands-on",
      +  "food",
      +  "market",
      +  "walk",
      +  "run",
      +  "learn",
      +  "heritage",
      +  "nature",
      +  "science",
      +  "lights",
      +  "fireworks",
      +  "books",
      +  "seasonal",
      +  "halloween",
      +  "christmas",
      +  "year-end",
      +  "new-year",
      +  "evening",
      +  "free",
      +  "partly-paid",
      +  "paid",
      +  "book-ahead",
      +  "walk-in"
      +]
    • changedOutput schema / properties / read / properties / tags / items / enum
      Previous value: -[
      -  "kids",
      -  "family",
      -  "teens",
      -  "adults",
      -  "seniors",
      -  "pets",
      -  "indoor",
      -  "outdoor",
      -  "watch",
      -  "hands-on",
      -  "food",
      -  "market",
      -  "walk",
      -  "learn",
      -  "heritage",
      -  "nature",
      -  "science",
      -  "lights",
      -  "fireworks",
      -  "books",
      -  "seasonal",
      -  "halloween",
      -  "christmas",
      -  "year-end",
      -  "new-year",
      -  "evening",
      -  "free",
      -  "partly-paid",
      -  "paid",
      -  "book-ahead",
      -  "walk-in"
      -]New value: +[
      +  "kids",
      +  "family",
      +  "teens",
      +  "adults",
      +  "seniors",
      +  "pets",
      +  "indoor",
      +  "outdoor",
      +  "watch",
      +  "hands-on",
      +  "food",
      +  "market",
      +  "walk",
      +  "run",
      +  "learn",
      +  "heritage",
      +  "nature",
      +  "science",
      +  "lights",
      +  "fireworks",
      +  "books",
      +  "seasonal",
      +  "halloween",
      +  "christmas",
      +  "year-end",
      +  "new-year",
      +  "evening",
      +  "free",
      +  "partly-paid",
      +  "paid",
      +  "book-ahead",
      +  "walk-in"
      +]
  2. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: no model call, same parsing rules as site chat, the interpretation recorded in 'read', and the default date window (today→weekend, fallback 60 days). It stops short of describing result ordering or truncation behavior, so it sits just above the annotation baseline.

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 bracketed lead ('[이번 주말: 축제·공연·전시 찾기]') front-loads the scope, then each sentence adds a distinct rule. It is dense but largely waste-free; the multilingual example list and the fallback-window sentence are the only mildly verbose parts.

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?

The tool is a read-only natural-language search with an output schema, so return values need no explanation here. What an agent needs before calling — parsing behavior, language support, date defaults, follow-up mechanics, and sibling routing — is all present.

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%, so limit, previous and question are already fully documented, and the schema itself explains the carry-over semantics of previous. The description mainly reinforces this with multilingual phrasing examples rather than adding syntax or constraints the schema lacks, putting it at the baseline.

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?

States a specific verb and resource ('한 문장으로 물으면 ... 행사를 찾습니다') and immediately bounds the domain to festivals/performances/exhibitions for the coming weekend. It explicitly distinguishes itself from the sibling search_events by saying search_events is more accurate when date and region are already known.

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

Usage Guidelines5/5

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

Gives the selecting condition (one natural-language sentence, multilingual, no explicit date/region needed) and names the alternative with its own condition ('날짜와 지역을 이미 알면 search_events가 더 정확합니다'). It also explains the follow-up case ('다음 주는?') and how to populate previous, leaving nothing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources