Skip to main content
Glama
Sign In
korea-finance-factcheck

korea-finance-factcheck

by hs85-newbie
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

check_unit_errors

Flags 10x or 100x unit errors in Korean finance articles by comparing company revenue, operating profit, and net income stated alongside the stock code against official DART filings.

Instructions

본문에 '회사명(종목코드)'와 함께 적힌 매출·영업이익·순이익이 DART 사업보고서 값과 10배·100배 어긋나는지 본다.

DART_API_KEY 가 필요하다. 조회가 안 되면 skipped 에 이유를 남긴다.

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_unit_errors"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose useful behavior: an external DART API dependency, the API key requirement, and the fallback of recording a reason in 'skipped' when lookup fails. It does not describe what a positive result looks like (which figures/fields are returned) or whether the check is read-only versus caching, leaving meaningful behavioral gaps.

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?

Three short sentences: purpose first, then prerequisite, then failure behavior — front-loaded and free of filler. The purpose sentence is dense but every clause conveys information.

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?

For a tool that depends on an external API key and can fail silently into a 'skipped' field, the description covers the prerequisite and the failure mode. It is still incomplete on output shape (no output schema exists) — an agent cannot tell what a successful detection result contains or how mismatches are reported.

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 coverage is 0% and the single 'text' parameter is bare, but the description compensates by explaining the expected content of that text: body text containing 'company name (ticker)' and the three financial line items. That is the essential semantic an agent needs to build a valid argument.

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 states a specific check: comparing revenue/operating profit/net income figures written alongside 'company name (ticker)' against DART annual report values for 10x/100x magnitude mismatches. That is concrete and distinguishes it reasonably from siblings like check_stock_closes or check_ratio_direction, though the underlying 'unit error' concept is only indirectly contrasted with those siblings.

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

Usage Guidelines3/5

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

Context is implied — the input text must contain a company name with ticker plus financial figures — and the DART_API_KEY prerequisite is stated. However, it never explicitly says when to prefer this over check_market_numbers, check_ratio_direction, or check_all, and gives no exclusions.

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

Deploy Server

Other Tools