Skip to main content
Glama

매동 (maedong) — Korean Market Signals

maedong_stock_signals

Read-onlyIdempotent

Signal history for one Korean stock (KOSPI/KOSDAQ) by its 6-digit code — which lists it appeared on and what happened after.

한 종목이 언제 어느 시그널에 걸렸고 그 뒤 어땠는지. '집계 전' 은 아직 그 거래일이 지나지 않은 것이며 0% 가 아니다. 전일 마감 데이터다. 응답 첫 줄의 기준일을 그대로 인용하고 '오늘' 로 바꿔 말하지 말 것. 인용할 때는 첫 줄의 출처(매동(maedong.kr))도 기준일과 함께 그대로 옮길 것. 과거 통계 조회 도구입니다. 특정 종목의 매수·매도 판단을 생성하는 데 사용하지 마세요.

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": {
      "code": "<code>"
    },
    "name": "maedong_stock_signals"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNo종료일 YYYY-MM-DD
codeYes6자리 종목코드 (예: 005930 · 우선주 등은 대문자 섞임: 00104K)
fromNo시작일 YYYY-MM-DD
limitNo기본 100
formatNo기본 text

Output Schema

NameRequiredDescriptionDefault
codeYes
hitsYes
metaYes
nameNo
noteNo
countNo
flagsNo
marketNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / code / description
      Previous value: -"6자리 종목코드 (예: 005930)"New value: +"6자리 종목코드 (예: 005930 · 우선주 등은 대문자 섞임: 00104K)"
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "properties": {
      +    "code": {
      +      "type": "string"
      +    },
      +    "count": {
      +      "type": "integer"
      +    },
      +    "flags": {
      +      "type": "array"
      +    },
      +    "hits": {
      +      "type": "array"
      +    },
      +    "market": {
      +      "type": "string"
      +    },
      +    "meta": {
      +      "type": "object"
      +    },
      +    "name": {
      +      "type": "string"
      +    },
      +    "note": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "code",
      +    "hits",
      +    "meta"
      +  ],
      +  "type": "object"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / format / description
      Added value: +"기본 text"
  4. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive, closed-world), yet the description still adds non-obvious data semantics: values reflect the prior trading day's close, a '집계 전' entry means the trading day has not yet passed rather than 0%, and the response's first line carries the as-of date and source attribution. Those disclosures materially change how an agent reads the output; only rate limits and pagination behavior are left unstated.

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

Conciseness3/5

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

The purpose statement is front-loaded and efficient, but the core English sentence is then restated verbatim in Korean, and several imperative sentences govern citation formatting ('quote the first-line date, don't say today, also carry the source'). Those rules are functional but repetitive, and the description spends more length on output-citation etiquette than on the tool's own behavior.

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 5 parameters at full schema coverage and an output schema present, the description does not need to explain return structure, and it usefully closes the remaining gaps around data freshness and the '집계 전' sentinel. The one gap is sibling differentiation — an agent choosing between this and the aggregate or current-signal tools gets no comparative cue.

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 code, from, to, limit, and format are already fully documented in the schema, including the 6-digit and uppercase-suffix examples. The description only restates '6-digit code' and adds no format syntax, default, or range meaning beyond the schema, so baseline 3 applies.

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 opening line names a specific verb and resource — signal history for one Korean stock by 6-digit code — and adds scope ('which lists it appeared on and what happened after'), which makes it distinguishable from a general signal-list tool. It stops short of naming a sibling (e.g. maedong_signals or maedong_signal_stats) to contrast with, so differentiation relies on inference from the tool name.

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?

The description explicitly frames the tool as a historical statistics lookup and states a clear exclusion: do not use it to generate buy/sell judgments for a specific stock. That is real when-not-to-use guidance, but no alternative tool is named for the cases it excludes, so the agent must find its own fallback.

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