Skip to main content
Glama
bitbank-lab-mcp

bitbank-lab-mcp

Official
by bitbankinc

get_volatility_metrics

Calculates ATR, realized volatility, Parkinson, Garman-Klass, and Rogers-Satchell metrics for crypto pairs across timeframes; supports annualization and rolling windows to track volatility changes.

Instructions

[Volatility / ATR / RV] ボラティリティ指標(volatility / ATR / realized vol)を算出。RV・ATR・Parkinson・Garman-Klass・Rogers-Satchell。年率換算対応。aggregates.atr は Wilder ATR(RMA ベース、period=14、TradingView 標準と一致)。ローリングではボラ変化を RV / Parkinson で追跡してください。

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": {
      "pair": "<pair>",
      "type": "<type>"
    },
    "name": "get_volatility_metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
tzNoAsia/Tokyo
pairYes
typeYes
viewNoview は content の量を制御します。量は summary < detailed < full の順で、full は常にそのツールの最重量です。view が structuredContent から**フィールドを削ることはありません**(その view でしか計算しないデータを足すツールはあり、その場合は当該 view の説明に明記しています)。content[0].text は LLM への唯一のチャネルなので、軽い view は「短い表示」ではなく「LLM が明細を受け取らない」を意味します。 本ツールの結論は aggregates / rolling(スカラー値)なので、**full でも系列そのものは content に出ない**(系列が必要なら get_candles を使う)。 - summary(既定): 集計 + ローリング分析 + 4 行フッタ。窓ごとの内訳・Assessment は content に出ない。 - detailed: summary + 【Volatility Metrics】/【Rolling Trends】/【Assessment】の内訳。系列の統計値は content に出ない。 - full: detailed + 【Series】(件数 / 期間 / Close レンジ / リターンの平均・標準偏差)。本ツールの最重量。 - beginner(**階梯外**): 平易な日本語 4 行。**専門用語・指標名・フッタは content に出ない**——読者向けレジスタを変える view であり、量の階梯には乗らない。summary
limitNo
windowsNo
annualizeNo
cacheTtlMsNo
useLogReturnsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields 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"
    • addedInput schema / properties / view / description
      Added value: +"view は content の量を制御します。量は summary < detailed < full の順で、full は常にそのツールの最重量です。view が structuredContent から**フィールドを削ることはありません**(その view でしか計算しないデータを足すツールはあり、その場合は当該 view の説明に明記しています)。content[0].text は LLM への唯一のチャネルなので、軽い view は「短い表示」ではなく「LLM が明細を受け取らない」を意味します。\n本ツールの結論は aggregates / rolling(スカラー値)なので、**full でも系列そのものは content に出ない**(系列が必要なら get_candles を使う)。\n- summary(既定): 集計 + ローリング分析 + 4 行フッタ。窓ごとの内訳・Assessment は content に出ない。\n- detailed: summary + 【Volatility Metrics】/【Rolling Trends】/【Assessment】の内訳。系列の統計値は content に出ない。\n- full: detailed + 【Series】(件数 / 期間 / Close レンジ / リターンの平均・標準偏差)。本ツールの最重量。\n- beginner(**階梯外**): 平易な日本語 4 行。**専門用語・指標名・フッタは content に出ない**——読者向けレジスタを変える view であり、量の階梯には乗らない。"
  2. First observedv0.1.1

TDQS

B3.4/5.0
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 disclose meaningful computation conventions: the exact estimator set, year-annualization support, and that aggregates.atr is Wilder ATR (RMA-based, period=14, matching TradingView). It omits cache behavior, return shape in the main body, and whether rolling windows align with the `windows` parameter, leaving some behavioral gaps for a 9-parameter tool.

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-loaded with a bracketed tag and the core action, followed by estimator list, a convention note, and a usage directive — no redundant sentences. It is dense but each sentence adds information; the main weakness is that the ATR-convention detail sits before any explanation of how windows/period interact.

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?

For a 9-parameter tool with no output schema and no annotations, the description covers the analytical substance (which estimators, annualization, Wilder ATR convention) but leaves several inputs unexplained, notably useLogReturns and the windows/limit/cache semantics. Adequate to pick the tool, insufficient to invoke it confidently across all parameters.

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

Parameters2/5

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

Schema description coverage is only 11% (just `view`), so the description must compensate for the other eight parameters and largely does not. It indirectly justifies `annualize` and hard-codes an ATR period of 14 without explaining how that relates to the `windows` array default [14,20,30], and says nothing about `useLogReturns`, `limit`, or `cacheTtlMs` — a material omission since log vs simple returns changes the RV/volatility numbers.

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?

States a specific verb+resource (compute volatility metrics) and enumerates the exact estimators returned: RV, ATR, Parkinson, Garman-Klass, Rogers-Satchell, plus annualization support. An agent can distinguish it from indicator-overview siblings like analyze_indicators, though no sibling is named in the main body to sharpen that boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The closing line gives one concrete usage rule — track volatility change with RV / Parkinson under rolling analysis — and the aggregates.atr note clarifies which ATR variant to trust. There is no explicit when-to-use-this-vs-another-tool guidance in the description itself; the only routing hint (use get_candles for raw series) lives inside the view parameter's schema text, not the description.

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