Skip to main content
Glama
Universal Quant Tournament MCP

Universal Quant Tournament MCP

run_multi_strategy_tournament

Runs an 8-strategy walk-forward tournament with macro-event, market-regime, session-liquidity and candle-confirmation filters to evaluate signals out-of-sample.

Instructions

Performs a top-down institutional market evaluation: (1) Pulls live ForexFactory high/medium impact macro events (forex_factory_macro_calendar) and checks forexfactory.com/calendar for scheduled news risk, (2) Classifies Higher-Timeframe (HTF) structure and market regime, (3) Filters historical and live signals by user-definable session liquidity hours using bar timestamps, (4) Requires price-action candle confirmation (Engulfing, Rejection Pinbar, or Displacement close) on the entry bar, and (5) Evaluates 8 quantitative strategies via a two-stage Out-of-Sample walk-forward backtest.

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": "run_multi_strategy_tournament"
  }
}

Input Schema

NameRequiredDescriptionDefault
symbolNoTicker or TradingView exchange:symbol (e.g., 'XAU/USD', 'OANDA:GBPJPY', 'NASDAQ:NVDA', 'BINANCE:BTCUSDT', 'CME_MINI:MNQ1!').NVDA
timeframeNoCandle interval for indicator & walk-forward backtest calculation.15Min
custom_barsNoOptional caller-supplied OHLCV bars array.
lookback_barsNoNumber of historical OHLCV bars to evaluate (60 to 2000).
session_filterNoSession liquidity filter applied to bar timestamps (UTC): 'auto', 'london_ny' (06-21 UTC), 'london_only' (07-16 UTC), 'ny_only' (12-21 UTC), 'london_ny_overlap' (12-16 UTC), 'us_equity_regular' (13-20 UTC), 'custom', or '24_7'.auto
session_end_utcNoCustom session end hour in UTC (0-24) when session_filter is 'custom'.
strategy_filterNoSet to 'all' for the full 8-strategy tournament, or specify a single strategy ID.all
session_start_utcNoCustom session start hour in UTC (0-23) when session_filter is 'custom'.
use_local_mt5_barsNoSet to true to pull live candles directly from the user's open local MetaTrader 5 terminal.
require_candle_confirmationNoRequire an entry-bar price-action trigger (Bullish/Bearish Engulfing, Rejection Pinbar, or Marubozu Displacement close) for signal_active.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

C2.9/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose meaningful internals: an external ForexFactory calendar pull, a website check, HTF regime classification, and a two-stage out-of-sample walk-forward. However, it never states whether the tool is purely analytical or can lead to execution, doesn't warn about runtime cost for up to 2000 bars across 8 strategies, and doesn't explain what happens if the MT5 terminal or the external calendar source is unavailable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The numbered structure front-loads the overall purpose effectively, but the single sentence is overloaded and includes implementation detail such as the literal forexfactory.com/calendar URL check that does little for tool selection. It is dense without being wasteful enough to be a serious problem, but it reads more like a process spec than a selection aid.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, high-complexity backtest pipeline with no output schema, the description says nothing about what the tournament returns (rankings, per-strategy metrics, equity curves, pass/fail) or how long it may take. An agent cannot judge result shape or cost from this definition, which is a substantial gap for a tool this heavy.

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 100%, so the baseline is 3; the schema already documents symbol format, timeframe enums, session windows, and the strategy list. The description reinforces a few parameters (session liquidity filtering in step 3, candle confirmation in step 4, the 8-strategy set for strategy_filter) but adds no syntax, precedence, or edge-case meaning beyond the schema.

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 names a specific composite operation (a multi-strategy walk-forward tournament) and enumerates its five constituent stages, so an agent can tell this is an analysis/backtest pipeline rather than an order builder or Monte Carlo stress test. It stops short of explicitly naming the siblings it is not, leaving differentiation to inference from the step list.

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

Usage Guidelines2/5

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

The numbered steps describe what happens internally, not when an agent should choose this tool over run_monte_carlo_stress_test or sync_or_execute_local_mt5, and no preconditions or exclusions are stated. The only conditional language is about requiring candle confirmation, which is a parameter default rather than usage guidance.

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