dart-risk-mcp

search_market_disclosures

Scan all Korean DART disclosures for preset risk signals (e.g., CB issuance, capital reduction) to detect early warnings of market-wide corporate risk.

Instructions

시장 전체 공시에서 preset에 해당하는 위험 신호를 일괄 스캔한다.

기업명을 지정하지 않고 전체 상장사 공시를 조회하므로, 특정 위험 신호가 시장에 얼마나 확산되어 있는지 조기경보로 활용할 수 있다.

사용법:

"최근 7일 동안 CB/BW 발행 공시 전수": search_market_disclosures("cb_issue", 7)
"최근 30일 자사주 취득 결정": search_market_disclosures("treasury", 30)
"최근 14일 감자 공시": search_market_disclosures("reverse_split", 14)

Args: preset: 신호 프리셋 — cb_issue / treasury / reverse_split / 3pca / shareholder_change / exec_change / audit_issue / asset_transfer / going_concern / delisting / embezzle / inquiry / fund_outflow / all_risk days: 조회 기간 (기본 7일, 최대 90일). from_date/to_date를 주면 무시된다. max_results: 최대 반환 건수 (기본 50, 최대 200) from_date: 조회 시작일(선택). "2024-01-01"·"20240101" 형식. to_date: 조회 종료일(선택). 미지정 시 오늘. confirm_long: 창이 길어 오래 걸리는 조회를 실제로 실행할지. 미지정 상태로 긴 창을 요청하면 예상 소요와 함께 안내만 반환한다.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`days`	No
`preset`	Yes
`to_date`	No
`from_date`	No
`max_results`	No
`confirm_long`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.21.25Sep 1, 2026

addedInput schema / properties / confirm_long

Added value: +{
+  "default": false,
+  "title": "Confirm Long",
+  "type": "boolean"
+}

addedInput schema / properties / from_date

Added value: +{
+  "default": "",
+  "title": "From Date",
+  "type": "string"
+}

addedInput schema / properties / to_date

Added value: +{
+  "default": "",
+  "title": "To Date",
+  "type": "string"
+}

First observedv1.0.3May 31, 2026

TDQS

A4.6/5.0

Behavior4/5

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

With no annotations, the description carries the disclosure burden. It covers non-obvious behavior such as confirm_long: an unconfirmed long-window request returns only guidance with estimated cost instead of executing. It also documents that days is ignored when from_date/to_date is provided and caps days at 90. It does not describe output contents or rate limits, but the output schema covers the return shape.

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

Conciseness5/5

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

The description is organized into a one-line purpose, a rationale sentence, three usage examples, and a compact Args list. Each section earns its place; the long preset enum is necessary and the date and confirmation details are behaviorally important. There is no fluff.

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 definition is self-contained for invocation: required preset, optional time windows, result caps, date formats, and the confirmation contract are all covered. Since an output schema exists, return-value detail is not needed here. The market-wide scope also resolves the primary ambiguity among sibling tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description fully compensates. It enumerates all preset values, defaults and caps for days and max_results, the accepted date formats for from_date/to_date, and the interaction between days and explicit dates. This is more parameter guidance than most structured schemas provide.

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?

The description opens with a specific verb and resource: market-wide disclosures are scanned in batch for risk signals matching a preset. It also distinguishes itself from company-specific siblings by explicitly stating that it queries all listed companies without a company name. As a market-level early-warning scan, its purpose is unmistakable.

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 gives clear context and concrete examples: '최근 7일 동안 CB/BW 발행 공시 전수' and the analogy of an early warning for how widely a risk signal has spread. It notes the contrast with company-specific queries, but it does not explicitly name sibling alternatives or state when-not-to-use, so it stops short of a 5.

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