tossinvest-mcp

Overview Schema Source Related Servers Discussions Admin

get_candles

Read-onlyIdempotent

Retrieve OHLCV candle data for Korean and US stocks, including 1-minute and daily bars, with newest-first results and pagination using the previous response's nextBefore value.

Instructions

종목의 캔들(OHLCV)을 최신순으로 조회한다 (분봉·일봉, 최대 200개).

과거로 넘기려면 응답의 nextBefore 를 before 에 넣는다. 1분봉은 국내 2022-11-23, 미국 2021-12-01 이전 데이터가 없다.

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": {
      "symbol": "<symbol>"
    },
    "name": "get_candles"
  }
}

Input Schema

Name	Required	Description	Default
`count`	No	봉 개수 (최대 200)
`before`	No	이 시각(ISO 8601, 포함) 이전 봉만 조회. 다음 페이지는 이전 응답의 nextBefore 값을 넣는다
`symbol`	Yes	종목 심볼. 국내는 6자리 종목코드(예: 005930), 미국은 티커(예: AAPL)
`adjusted`	No	수정주가 적용 여부
`interval`	No	봉 단위: 1m 분봉, 1d 일봉	1d

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Even though the annotations already declare readOnly=true, idempotent=true and openWorld=true, the description adds real behavioral context: results come back newest-first, are capped at 200, use a cursor for pagination, and have historical depth limits for 1-minute data that vary by market. It does not discuss error behavior or adjusted-price semantics.

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?

Three short sentences, front-loaded with what the tool returns and its cap, then the paging rule, then the data-availability constraint. Nothing is redundant with the schema or the annotations.

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?

Given five parameters, no output schema and safe annotations, the description covers the essentials: ordering, limit, pagination, and the historical limits. The one gap is that it introduces the nextBefore return field without describing the rest of the response shape; this is minor for a read-only listing tool.

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?

Because schema coverage is 100%, the baseline is 3, and the description earns more by explaining the relationship between the two parameters that matters for paging: nextBefore from the response goes into before. It also ties the interval parameter to the data-availability caveat.

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 and resource (캔들 OHLCV 조회), plus scope details: newest-first ordering, minute/day intervals, and a cap of 200 candles. It does not explicitly distinguish this tool from its sibling get_prices or from get_market_indicator_candles, so the agent must infer the boundary.

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 tells the agent exactly how to page backwards (put nextBefore from the response into before) and warns about the earliest available 1-minute data by market (KR 2022-11-23, US 2021-12-01). It never states when to prefer get_prices or get_market_indicator_candles instead, so it has no exclusions or alternatives.

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