Analysis Tools

Analysis tools operate on your trade history (R-multiples, equity values, P&L) to reveal the structure of your edge.

analyze_drawdown

Cost: $0.005 | Analyze drawdown periods from an equity curve.

result = client.call_tool(
    "analyze_drawdown",
    equity_values=["100000", "101500", "99800", "102000", "98500", "103000"],
    starting_equity="100000",
)

Returns: max_drawdown_pct, max_drawdown_usd, current_drawdown, avg_drawdown, drawdown_count, longest_duration, time_in_drawdown, recovery_factor, ulcer_index, drawdown_periods.

run_monte_carlo

Cost: $0.008 | Simulate future equity paths using historical R-multiples.

result = client.call_tool(
    "run_monte_carlo",
    r_multiples=["1.5", "-1.0", "2.3", "-0.5", "1.8", "-1.0"],
    starting_equity="100000",
    num_simulations=5000,
)

Returns: probability_of_profit, probability_20pct_gain, probability_20pct_drawdown, probability_50pct_drawdown, median_final_equity, p5_final_equity, p95_final_equity, mean_final_equity, best_case, worst_case.

calculate_kelly

Cost: $0.004 | Calculate Kelly criterion position sizing fractions.

result = client.call_tool(
    "calculate_kelly",
    r_multiples=["1.5", "-1.0", "2.3", "-0.5", "1.8", "-1.0", "3.2", "0.8"],
)

Returns: full_kelly, half_kelly (recommended), quarter_kelly (conservative), risk_of_ruin.

find_variance_killers

Cost: $0.006 | Identify trades that damage geometric growth the most.

A variance killer is a trade whose deviation from the mean hurts G, even if individually profitable. High variance erodes geometric returns.

result = client.call_tool(
    "find_variance_killers",
    r_multiples=["1.5", "-1.0", "2.3", "-0.5", "1.8", "-1.0", "3.2", "0.8", "-2.5"],
)

Returns: top 5 killers each with index, r_multiple, g_impact, variance_contribution, potential_g_improvement.

analyze_win_loss

Cost: $0.004 | Calculate win/loss statistics from R-multiples.

result = client.call_tool(
    "analyze_win_loss",
    r_multiples=["1.5", "-1.0", "2.3", "-0.5", "1.8", "-1.0", "3.2", "0.8"],
)

Returns: win_rate, loss_rate, avg_win_r, avg_loss_r, avg_win_usd, avg_loss_usd, payoff_ratio, profit_factor, expectancy, net_pnl.

run_what_if

Cost: $0.008 | Explore G improvement scenarios.

Shows how G would change if losses were capped at different levels, or if the worst trades were avoided.

result = client.call_tool(
    "run_what_if",
    r_multiples=["1.5", "-1.0", "2.3", "-0.5", "1.8", "-1.0", "3.2", "0.8", "-2.5"],
)

Returns: loss_cap_scenarios (G at -0.5R, -1R, -1.5R, -2R caps), avoidance_scenarios (G after removing worst 5%/10%/15%/20% of trades), top_variance_killers.

detect_regime

Cost: $0.006 | Detect current market regime from OHLCV bars.

Classifies: TRENDING_UP, TRENDING_DOWN, RANGING, LOW_VOLATILITY, VOLATILE.

result = client.call_tool(
    "detect_regime",
    bars=[{"open": "150.00", "high": "152.00", "low": "149.50", "close": "151.50", "volume": "5000000"}, ...],
)

Returns: regime, trend_direction, trend_strength, volatility_state, volatility_percentile, atr.

analyze_confidence

Cost: $0.005 | Confidence interval analysis on R-multiples. Returns mean, standard deviation, and confidence bounds at 90%, 95%, and 99% levels.

analyze_consistency

Cost: $0.005 | Measure trading consistency. Compares recent performance windows to detect behavioral drift.

analyze_correlation

Cost: $0.005 | Correlation analysis between R-multiples and external factors. Detects serial correlation in trade outcomes.

analyze_distribution

Cost: $0.005 | Analyze the statistical distribution of R-multiples. Returns skewness, kurtosis, normality test, percentiles, and tail risk.

analyze_recovery

Cost: $0.005 | Analyze recovery patterns after drawdowns. Returns average recovery time, recovery R needed, and worst recovery period.

analyze_risk_adjusted

Cost: $0.005 | Risk-adjusted return metrics. Returns Sharpe-like ratio, Sortino equivalent, Calmar ratio, and risk-adjusted G.

segment_trades

Cost: $0.005 | Analyze G metrics by segment to find where your edge lives.

result = client.call_tool(
    "segment_trades",
    trades=[
        {"pnl_r": "1.5", "pnl_usd": "750", "symbol": "AAPL"},
        {"pnl_r": "-0.8", "pnl_usd": "-400", "symbol": "MSFT"},
        {"pnl_r": "2.0", "pnl_usd": "1000", "symbol": "AAPL"},
    ],
    segment_by="symbol",
)

Returns per-segment: g, expected_r, variance, win_rate, total_pnl, helps_g (bool).

analyze_execution_quality

Cost: $0.005 | Analyze trade execution using MAE/MFE analysis.

Returns: avg_mae_r, avg_mfe_r, entry_efficiency, exit_efficiency, avg_winner_hold_time, avg_loser_hold_time.

detect_peak_valley

Cost: $0.005 | Detect peaks and valleys in an equity curve.

Returns: ath_count, atl_depth, avg_peak_to_valley_drop, avg_valley_to_peak_gain, current_state (AT_PEAK, AT_VALLEY, BETWEEN).

calculate_rolling_g

Cost: $0.005 | Calculate rolling G over sliding windows to track edge evolution.

result = client.call_tool(
    "calculate_rolling_g",
    r_multiples=["1.5", "-1.0", "2.3", "-0.5", "1.8", "-1.0", "3.2", "0.8"],
    window_size=5,
)

Returns: rolling_g_values, trend (IMPROVING, STABLE, DECLINING), trend_slope.

calculate_system_r_score

Cost: $0.005 | Calculate the System R Score (0 to 100 composite grade) from R-multiples.

Returns: score (0 to 100), grade (A+ through F), components breakdown.