dart-risk-mcp

build_event_timeline

Orders Korean DART disclosure events chronologically to reveal manipulation narratives, classify entry, control-change, and distress stages, and match known crisis patterns.

Instructions

기업의 공시 이벤트를 시간순으로 정렬해 조작 흐름의 서사를 구성한다.

각 이벤트를 진입기(자금 조달/경영권 진입), 심화기(지배구조 변화), 탈출기(의심/수사/부실) 단계로 분류하고, 알려진 위기 패턴과 매칭한다.

공개기록 레지스트리(opt-in)가 설정돼 있고 이 회사가 등재 행위자의 관련기업으로 태깅된 경우, 리포트 말미에 공개기록 참고 섹션이 추가된다.

Args: company_name: 기업명 (예: "에코프로") 또는 종목코드 6자리 (예: "086520") lookback_years: 조회 기간(년). 기본 1년, 1~5년 범위. 1년을 넘으면 원문 사실 블록 없이 신호·패턴·타임라인만 담은 "지도"가 된다. from_date: 조회 시작일(선택). "2024-01-01"·"20240101" 형식. 주면 lookback_years는 무시된다. to_date: 조회 종료일(선택). 미지정 시 오늘. from_date만 주면 그날부터 오늘까지, to_date만 주면 그날 기준 1년.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`to_date`	No
`from_date`	No
`company_name`	Yes
`lookback_days`	No
`lookback_years`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.21.25Sep 1, 2026

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"
+}

Changed4 schema fields changedv1.4.0Jun 21, 2026
- addedInput schema / properties / lookback_days / anyOf
```
Added value: +[
+  {
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]
```
- changedInput schema / properties / lookback_days / default
```
Previous value: -365New value: +null
```
- removedInput schema / properties / lookback_days / type
```
Removed value: -"integer"
```
- addedInput schema / properties / lookback_years
```
Added value: +{
+  "default": 1,
+  "title": "Lookback Years",
+  "type": "integer"
+}
```
First observedv1.0.3May 31, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations provided, the description carries the full behavioral burden. It discloses not only the sorting behavior but also the automated stage classification, crisis-pattern matching, and a conditional public-record reference section that appears only under specific opt-in and tagging conditions. This adds meaningful behavioral detail beyond the schema.

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 description is front-loaded with the primary purpose, followed by behavioral detail and parameter semantics. Each sentence adds useful information, and the Args section is organized. The formatting appears slightly cramped or truncated around lookback_years and from_date, which slightly hurts readability but not substance.

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?

The description covers the tool's purpose, behavior, conditional output sections, and most parameters. Because output schema exists, not describing return values is acceptable. However, the undocumented lookback_days parameter, missing date format, and lack of any sibling differentiation prevent the description from being fully complete for correct tool selection and invocation.

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 0%, so the description must compensate. It does document company_name (accepts name or six-digit code), lookback_years (default 1, range 1–5), and from_date/to_date behavior (including default ranges when only one is given). However, lookback_days is omitted entirely and no date format is specified, leaving a real gap for an agent attempting correct invocation.

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 clearly states the tool's function with a specific verb and resource: it sorts a company's disclosure events chronologically to build a manipulation-flow narrative. It goes beyond the name by describing the three-stage classification (entry, deepening, exit) and matching against known crisis patterns, which distinguishes it from raw disclosure-listing siblings.

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 provides clear context for when this tool is useful: when an agent needs a chronological, pattern-matched narrative of events rather than a simple list of disclosures. It does not explicitly name alternatives or when-not-to-use cases, which prevents a 5, but the intended use case is clear.

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