Skip to main content
Glama
bitbank-lab-mcp

bitbank-lab-mcp

Official
by bitbankinc

prepare_chart_data

Prepare chart-ready OHLCV data for visualization, with optional technical indicators and timezone formatting for market analysis.

Instructions

[Chart / Candlestick / Visualization] チャート描画の第一選択ツール。

⚠️ limit はデフォルト 30 を推奨。ユーザーが期間を明示した場合のみ増やすこと。 indicators はユーザーが明示的に要求した指標のみ指定すること。分析のついでに追加しない。 indicators の同時指定はコンテキストを大幅に消費するため、必要最小限に留めること。

デフォルトはローソク足(OHLCV)のみ返す。indicators 未指定 = ローソク足のみ。 指標が必要な場合は indicators に明示指定: SMA_5, SMA_20, SMA_25, SMA_50, SMA_75, SMA_200, EMA_12, EMA_26, EMA_50, EMA_200, BB, ICHIMOKU, RSI, MACD, STOCH

レスポンス形式: { times[], labels?[], candles: [[o,h,l,c,v],...], series?: {指標名: values[]}, subPanels?: {...} } ローソク足は取引所の価格のまま。指標の値は価格の水準に合わせて丸め済み(10 万円以上は円の整数、安いペアほど小数の桁が増える)。全 null 系列は自動除外。

tz パラメータ(例: "Asia/Tokyo")指定時、times がローカル時刻に変換され、labels("03/16 17:00" 等の短縮表示文字列)も付加される。

SVG/PNG ファイル保存 → render_chart_svg。指標の最新値やトレンド判定 → analyze_indicators。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "prepare_chart_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
tzNoタイムゾーン(デフォルト: Asia/Tokyo)。times をローカル時刻に変換し、labels(短縮表示文字列)も付加する。空文字でUTCのみAsia/Tokyo
pairNobtc_jpy
typeNo1day
limitNo
indicatorsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.1
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observedv0.1.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the default output (candles only when indicators are omitted), that indicator values are rounded to price scale, that all-null series are dropped automatically, and that indicator requests consume significant context. It does not mention data freshness, rate limits, or failure behavior.

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?

Front-loads the core identity, then separates constraints, defaults, indicator vocabulary, response shape, and downstream routing into distinct blocks. Every section carries usable information; the repeated mention of 'no indicators = candles only' is minor redundancy but reinforces the default.

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?

There is no output schema, so the inline response-format sketch (times, labels, candles tuples, series, subPanels) is essential and well placed. For a 5-parameter data-preparation tool it is nearly complete, with only pair/type semantics left undocumented.

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 only 20% (only tz is documented in-schema), so the description must compensate, and it largely does: it explains the limit default and when to raise it, enumerates the permitted indicator values, and explains the tz conversion effect including label generation. pair and type get no semantic explanation beyond their schema defaults, which is the remaining gap.

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?

Opens with a bracketed category tag and states it is the first-choice tool for chart rendering, producing OHLCV candles plus optional indicator series. That is a specific verb+resource an agent can act on. It does not explicitly distinguish itself from the sibling get_candles, which appears to return overlapping raw data.

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?

Gives concrete operational guidance: keep limit at the default 30 unless the user names a period, request only indicators the user asked for, and don't add indicators as an analysis afterthought. It also routes downstream: file rendering goes to render_chart_svg and latest-value/trend questions go to analyze_indicators. The only gap is no explicit rule for when to prefer get_candles instead.

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