Skip to main content
Glama
korea-finance-factcheck

korea-finance-factcheck

check_stock_closes

Verifies stock closing prices cited in Korean finance articles against official KRX closing data, flagging mismatches and requiring an as-of date.

Instructions

'삼성전자(005930) … 종가 214,500원'처럼 적힌 종목 종가를 한국거래소(KRX) 공식 종가와 대조한다.

등락률은 보지 않는다. KRX_API_KEY 가 필요하고, KRX Open API 약관상 비상업 목적에만 쓸 수 있다. as_of 는 글을 쓴 날(YYYY-MM-DD). 없으면 본문의 '작성: 날짜' 줄, 그것도 없으면 오늘.

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": {
      "text": "<text>"
    },
    "name": "check_stock_closes"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
as_ofNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses an external dependency (KRX Open API), an authentication requirement (KRX_API_KEY), and a legal/usage restriction (non-commercial only). It does not say what happens on a missing key, a network/API failure, or what the comparison result looks like.

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 what is checked, then what is out of scope, then prerequisites, then the parameter fallback — a sensible order with little waste. The opening quoted fragment is slightly less scannable than a plain statement of purpose would be, but it earns its place by showing the accepted input format.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and the description never says what is returned — presumably a mismatch report per ticker, but an agent cannot know the shape or whether it gets a pass/fail, a list of discrepancies, or a corrected price. For a two-input check tool with no annotations this is the main remaining gap; everything else needed to invoke it is present.

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 description coverage is 0%, so the description must compensate and largely does: as_of gets a format (YYYY-MM-DD), a meaning (the article's writing date), and an explicit default-resolution order (본문 '**작성**:' line, else today). The text parameter is only implied via the example snippet rather than stated outright as 'the article body containing the quoted price'.

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 gives a specific verb (대조한다/cross-check) and resource (종목 종가, KRX official closing price) and anchors it with a concrete example of the input pattern ('삼성전자(005930) … 종가 214,500원'). It also states explicitly what it does not do (등락률은 보지 않는다), which helps distinguish it from the ratio/direction siblings, though no sibling is named directly.

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 clarifies scope ('등락률은 보지 않는다'), states the prerequisite (KRX_API_KEY) and the licensing restriction (비상업 목적 only), and gives a deterministic fallback chain for as_of. What's missing is naming the alternative tools (e.g. check_ratio_direction) that should be used instead when change rates are the question.

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