Skip to main content
Glama
anboyu-alt

dart-risk-mcp

by anboyu-alt
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

compare_financials

Compare financial statements of up to 20 Korean companies side by side across up to 10 years, covering revenue, operating profit, net income, assets, and liabilities.

Instructions

여러 기업의 재무제표를 나란히 비교한다 (최대 20개 기업 · 최대 10개 연도).

매출액·영업이익·당기순이익·자산총계·부채총계를 기본으로 내고, accounts로 좁힐 수 있다. year_to를 주면 그 구간을 연도별로 조회해 시계열로 낸다.

⚠ 조회 콜은 회사 수와 무관하게 연도 수만큼이다 — fnlttMultiAcnt가 corp_code를 콤마로 묶어 한 번에 받는다(실측 2026-09-11: 20개사 1콜 606행, 누락 0). 연도 폭 상한 10이 곧 콜 상한이다.

Args: company_names: 비교할 기업명 목록 (220개). year: 사업연도 4자리. 미입력 시 직전 연도. year_to: 구간의 끝 사업연도. 주면 yearyear_to를 시계열로 낸다. report_type: "annual" | "half" | "q1" | "q3". accounts: 계정명 부분일치 목록. 미지정이면 응답의 전 계정.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNo
year_toNo
accountsNo
report_typeNoannual
company_namesYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.26.3
    • addedInput schema / properties / accounts
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Accounts"
+}
    • addedInput schema / properties / report_type
      Added value: +{
+  "default": "annual",
+  "title": "Report Type",
+  "type": "string"
+}
    • addedInput schema / properties / year_to
      Added value: +{
+  "default": "",
+  "title": "Year To",
+  "type": "string"
+}
  2. First observedv1.0.3

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does so well: it discloses the API call-count model (calls scale with years, not companies), the underlying endpoint fnlttMultiAcnt, and even an empirical observation (20 companies = 1 call, 606 rows, 0 missing). It doesn't cover error behavior or return schema details, but has an output schema so that's acceptable.

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-loads the core purpose, then adds operational detail and parameter semantics. The call-count paragraph and empirical evidence are valuable but slightly verbose; still every line earns its place for a complex tool.

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?

Covers purpose, scope limits, parameter meanings, defaults, the call/performance model, and constrains behavior. Output schema exists so return format is covered. Missing only explicit sibling routing and error/permission notes.

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 it does: it defines each parameter (company_names count range, year default = prior year, year_to as range end, report_type with enum values, accounts as partial-match list) plus the default accounts returned.

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?

States a specific verb (비교한다 / compare) and resource (재무제표 / financial statements) with explicit scope limits (max 20 companies, max 10 years). Clearly distinguished from siblings like get_financial_summary (single company) and get_financial_statements_full by the multi-company comparison framing.

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?

Implies usage through limits (2-20 companies) and the year_to timeseries mode, and contrasts with the single-call design vs per-year calls. Does not explicitly name sibling alternatives (e.g., get_financial_summary for one company), but context is clear enough to select correctly.

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