Skip to main content
Glama
Finance Toolkit

Finance Toolkit

risk

Read-onlyIdempotent

Compute VaR, CVaR, drawdowns, GARCH volatility, skewness, kurtosis, and tail dependence from ticker data to quantify portfolio downside and stress exposure.

Instructions

Pre-computed risk metrics (VaR incl. historic/gaussian/cornish-fisher/studentt/evt distributions, CVaR, EVaR, GARCH volatility, max drawdown, drawdown duration, drawdown recovery time, drawdown series (underwater curve, the current distance from the running high; recovery=true gives the gain needed to get back to the high instead, e.g. +25% after a 20% fall; deepest_since=true adds the last date the drawdown was as deep), drawdown table (the top= deepest drawdowns with peak, trough and recovery dates, the gain needed from the trough back to the peak and lengths in periods and in calendar days and years), Conditional Drawdown at Risk (CDaR), Tail Ratio, skewness, kurtosis, downside deviation, Variance, Volatility incl. close_to_close/parkinson/garman_klass/rogers_satchell/yang_zhang estimators, Excess Volatility). VaR, CVaR, skewness, kurtosis, CDaR, Tail Ratio, downside deviation, Variance, Volatility and Excess Volatility support rolling=N for a rolling N-period value spanning the full history instead of one value per period (e.g. period='monthly', rolling=6 for a rolling 6-month figure). Requires tickers='AAPL' — use comma-separated values for multiple tickers. Supports period='daily' for whole-series calculations; rolling and per-period outputs use weekly, monthly, quarterly, or yearly. get_copula_simulation returns 100 simulated joint draws unless n_simulations= asks for more. get_tail_dependence_coefficient pairs ticker_a= (every ticker by default) with ticker_b= (the benchmark by default). get_covar measures the tail risk of ticker= (the system, the benchmark by default) given the distress of conditioning_ticker= (every other ticker by default), so by default how much each ticker's distress adds to the benchmark's tail risk (Delta-CoVaR). get_amihud_illiquidity is the price impact per billion dollars traded (scale=1e9). get_factor_analysis: factor analysis (predictive power) of the risk metrics across tickers: do the tickers that score high on one go on to return more than those that score low? Needs tickers= with at least ten, preferably twenty or more tickers. metrics= a risk metric name, a comma-separated list, or a collection: 'anomalies' (default: volatility, maximum drawdown, skewness, Amihud illiquidity) or 'all' (adds downside deviation, kurtosis, VaR, CVaR, tail ratio, Roll spread); each is measured within every period. Returns a row per metric and horizon: the mean information coefficient (IC, the Spearman rank correlation between the metric and the later returns), its standard deviation, IC information ratio, t-statistic, p-value, share of positive periods, number of periods, the Top Minus Bottom quantile spread, quantile turnover and rank autocorrelation. detail='information_coefficient', 'quantile_returns', 'quantile_turnover' or 'rank_autocorrelation' returns that part per period (or per quantile) for a single metric. period= sets how often it is evaluated (monthly by default), horizons= the periods ahead (e.g. 12 or [1, 12]), quantiles= the number of quantiles (5). Other parameters (e.g. alpha=) pass to the metrics. The IC is reported as measured: a negative IC for the volatility is the low-volatility anomaly. get_move_significance says how unusual each move is: the return in units of the volatility of the window= returns before it, the VaR Multiple (the return divided by the size of the historic VaR at alpha=, 0.05 by default, of those returns; below -1 is a VaR exceedance), its percentile among all earlier moves and the date of the last move as large in the same direction ('the biggest fall since'); use limit=-1 for the latest day and a start_date years back for a long history.

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": {
      "indicator": "<indicator>"
    },
    "name": "risk"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoThe number of upper order statistics to use. If a float in (0, 1) it is interpreted as the fraction of the strictly positive observations to use. A period without such observations reports NaN with 0 observations used.
qNoThe threshold quantile used for the "empirical" method, in (0.5, 1).
dofNoThe degrees of freedom of the Student-T copula, only used when `method="student-t"`.
lagNoNumber of periods to lag when computing growth rates.
topNoThe number of drawdowns per asset, deepest first.
lagsNoThe number of lags (past periods) the test or model uses, e.g. 1 or 5.
rankNotrue ranks the tickers (or countries) within every period, from the highest value (rank 1) to the lowest, and compares each with its neighbour toward the middle of the ranking: the Difference (in points for returns) and the Multiple (only when both have the same sign), so the first and last rank show how far the best and the worst stand apart, e.g. a fall more than twice as large as the next one. Needs a value per period and ticker; pick one field with show_columns where there are more.
tailNoWhich tail to estimate, one of "left" (the loss tail) or "right" (the gain tail).left
testNoWhich test(s) to run, one of "kupiec", "christoffersen" or "both".both
alphaNoThe tail probability (e.g., 0.05 for the 95% confidence level).
limitNoThe rows to return, like head and tail: 5 for the first five, -5 for the last five (the most recent of a time series). A table with its periods as columns (financial statements, ratios) keeps its first or last periods instead, and rows per ticker (an earnings calendar) are selected per ticker. For ETF holdings the largest (or, negative, the smallest) by weight, and for a list (e.g. news or a screener) its length. 0 returns every row.
scaleNoA multiplier applied to the resulting ratio purely for readability. Leave unset to use the default of the indicator you selected. Defaults are 1000000000 for get_amihud_illiquidity.
columnNoThe price column to use, e.g. 'Close' or 'Adj Close'; for get_factor_analysis the output of a metric with several, e.g. 'Signal Line'. Leave unset to use the default of the indicator you selected. Defaults are 'Return' for get_best_fitting_copula, get_component_value_at_risk, get_copula_parameters, get_copula_simulation, get_covar, get_marginal_value_at_risk, get_tail_dependence_coefficient; None for get_factor_analysis.
copulaNoFor get_copula_parameters: The copula family to fit, one of "gaussian", "student-t", "clayton", "gumbel" or "frank". For get_copula_simulation: The copula family to fit and simulate from, one of "gaussian", "student-t", "clayton", "gumbel" or "frank".gaussian
detailNoget_factor_analysis only: 'information_coefficient', 'quantile_returns', 'quantile_turnover' or 'rank_autocorrelation' returns that part for a single metric instead of the summary.
fisherNoWhether to use Fisher's definition of kurtosis (kurtosis = 0.0 for a normal distribution).
growthNoReturn period-over-period growth rates instead of absolute values.
methodNoFor get_tail_dependence_coefficient: The estimation method, one of "empirical", "gaussian" or "student-t". For get_volatility: Which Volatility estimator to use, one of "close_to_close", "parkinson", "garman_klass", "rogers_satchell" or "yang_zhang". Leave unset to use the default of the indicator you selected. Defaults are 'close_to_close' for get_volatility; 'empirical' for get_tail_dependence_coefficient.
periodNoObservation frequency, e.g. 'daily', 'weekly', 'monthly', 'quarterly', or 'annual' (supported values differ per method). Leave unset to use the default of the indicator you selected. Defaults differ between indicators.
tickerNoThe asset whose conditional VaR is being measured (the system).
windowNoThe number of periods the indicator looks back over, e.g. 14 or 20.
horizonNoThe number of days ahead to forecast.
lambda_NoThe decay factor. Higher values weight the past more heavily (slower to react), lower values weight recent returns more heavily (faster to react). RiskMetrics uses 0.94 for daily data.
max_lagNoThe maximum lag, included, to use when estimating the exponent: the regression runs over the lags 2 up to and including `max_lag`.
metricsNoget_factor_analysis only: the metric(s) to analyse, a method name such as 'get_price_to_earnings_ratio', a comma-separated list, or a collection of the tool (see the tool description), e.g. 'profitability'.anomalies
rollingNoRolling window size in number of periods. When set, the metric is computed over a smoothly overlapping trailing window across the full history (e.g. period='monthly' and rolling=6 gives a rolling 6-month value) instead of one value per period, or (for economics indicators) a simple moving average used to smooth the raw series. Leave unset to use the default of the indicator you selected. Defaults are None for get_conditional_drawdown_at_risk, get_conditional_value_at_risk, get_downside_deviation, get_excess_volatility, get_kurtosis, get_skewness, get_tail_ratio, get_value_at_risk, get_variance, get_volatility; 14 for get_ulcer_index.
tickersNoComma-separated ticker symbols, e.g. 'AAPL,MSFT,GOOGL'.
weightsNoPortfolio weights keyed by ticker. Normalized internally to sum to 1.
end_dateNoEnd of the date range in YYYY-MM-DD format; left empty, today (or the indicator's own window).
horizonsNoThe number of periods the forward returns cover.
recoveryNoWhether to return the gain needed to get back to the running peak (Recovery Needed) instead of the drawdown.
ticker_aNoThe first asset.
ticker_bNoThe second asset.
estimatorNoHow to construct the daily Realized Variance input, one of "squared_return", "parkinson", "garman_klass" or "rogers_satchell".squared_return
indicatorYesName of the specific metric to calculate, one of the listed values. Required — search_metrics finds the indicator (and its tool) for a metric by name.
quantilesNoThe number of quantiles the tickers are sorted into per period.
quarterlyNoReturn quarterly data instead of annual when True.
start_dateNoStart of the date range in YYYY-MM-DD format; left empty, five years before today (or the indicator's own window).
time_stepsNoTime steps to calculate GARCH for. Leave unset to use the default of the indicator you selected. Defaults are 10 for get_garch_forecast, get_gjr_garch_forecast; None for get_garch, get_gjr_garch.
n_bootstrapNoThe number of bootstrap resamples used to estimate the Standard Error of Z2.
standardizeNoReturn the Z-Score (standard score) instead of the raw values, i.e. how many standard deviations each value is from the mean of its own series. When combined with growth=True, the growth values are standardized instead of the raw values.
window_sizeNoFor get_acerbi_szekely_test: The rolling window size (in number of return observations) used to estimate each VaR/CVaR value. For get_var_backtest: The rolling window size (in number of return observations) used to estimate each VaR value.
distributionNoThe distribution to use for the rolling VaR estimates, one of "historic", "gaussian", "studentt" or "evt".historic
random_stateNoFor get_acerbi_szekely_test: The seed for the bootstrap random number generator. For get_copula_simulation: The seed for the random number generator.
show_columnsNoComma-separated names to filter the output. For historical data use the key names visible in any response record (e.g. 'Close,Volume,Return'). For financial statements use the 'metric' field values from the response (e.g. 'Revenue,Net Income,EBITDA'). Call the tool once without this parameter to see all available names, then repeat with show_columns to reduce response size and token usage.
deepest_sinceNoWhether to add the Deepest Since date of every period below the peak.
n_simulationsNoThe number of joint draws to simulate. Leave unset to use the default of the indicator you selected. Defaults are 100 for get_copula_simulation.
periods_apartNoThe number of periods between the dates the quantile turnover and the rank autocorrelation compare.
weekly_windowNoThe trailing window (in trading days) for the weekly RV component.
within_periodNoWhether to calculate GJR-GARCH within each specified period or all at once.
monthly_windowNoThe trailing window (in trading days) for the monthly RV component.
optimization_tNoFor get_garch: Time steps to optimize GARCH for. It is only used if no weights are given. For get_garch_parameters, get_gjr_garch_parameters: Time steps of the returns series to use for the optimization. For get_gjr_garch: Time steps to optimize GJR-GARCH for. It is only used if no weights are given.
risk_free_rateNoThe US Treasury yield used as the risk-free rate: '13w' (the 13-week bill), '5y', '10y' (default) or '30y'.10y
benchmark_tickerNoTicker used as the market benchmark, e.g. 'SPY' or '^GSPC'; 'None' for no benchmark.SPY
empirical_marginsNoWhether to map the simulated pseudo-observations back to realistic returns via each asset's own empirical (historical) quantile function. When False, the raw pseudo-observations (each in (0, 1)) are returned instead.
show_full_resultsNoOnly relevant when neither ticker is given. When False (the default), returns a square ticker-by-ticker grid of just the winning copula family per pair. When True, returns one row per pair instead, with the winning family's fitted parameter(s), Lower and Upper Tail Dependence, Log-Likelihood,...
conditioning_tickerNoThe asset whose distress `ticker` is conditioned on.
threshold_percentileNoOnly used when distribution='evt'. The percentile of losses above which the Generalized Pareto Distribution is fitted, e.g. 0.95 fits on the worst 5% of losses.
minimum_acceptable_returnNoThe minimum acceptable return (MAR) threshold below which returns are considered downside, e.g. 0.0 for downside relative to a zero return.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.3.4
    • addedInput schema / properties / rank
      Added value: +{
      +  "default": false,
      +  "description": "true ranks the tickers (or countries) within every period, from the highest value (rank 1) to the lowest, and compares each with its neighbour toward the middle of the ranking: the Difference (in points for returns) and the Multiple (only when both have the same sign), so the first and last rank show how far the best and the worst stand apart, e.g. a fall more than twice as large as the next one. Needs a value per period and ticker; pick one field with show_columns where there are more.",
      +  "type": "boolean"
      +}
  2. Changed6 schema fields changedv2.3.3
    • changedInput schema / properties / conditioning_ticker / description
      Previous value: -"The asset (or e.g. a benchmark/index) whose distress `ticker` is conditioned on. Leave unset to use the default of the indicator you selected. Required by: get_covar."New value: +"The asset whose distress `ticker` is conditioned on."
    • addedInput schema / properties / deepest_since
      Added value: +{
      +  "default": false,
      +  "description": "Whether to add the Deepest Since date of every period below the peak.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / risk_free_rate
      Added value: +{
      +  "default": "10y",
      +  "description": "The US Treasury yield used as the risk-free rate: '13w' (the 13-week bill), '5y', '10y' (default) or '30y'.",
      +  "enum": [
      +    "13w",
      +    "5y",
      +    "10y",
      +    "30y"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / ticker / description
      Previous value: -"The asset whose conditional VaR is being measured. Leave unset to use the default of the indicator you selected. Required by: get_covar."New value: +"The asset whose conditional VaR is being measured (the system)."
    • changedInput schema / properties / ticker_a / description
      Previous value: -"The first asset. Leave unset to use the default of the indicator you selected. Required by: get_tail_dependence_coefficient. Defaults are None for get_best_fitting_copula, get_copula_parameters, get_copula_simulation."New value: +"The first asset."
    • changedInput schema / properties / ticker_b / description
      Previous value: -"The second asset. Leave unset to use the default of the indicator you selected. Required by: get_tail_dependence_coefficient. Defaults are None for get_best_fitting_copula, get_copula_parameters, get_copula_simulation."New value: +"The second asset."
  3. Changed15 schema fields changedv2.3.2
    • addedInput schema / properties / column / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / column / default
      Previous value: -"Return"New value: +null
    • changedInput schema / properties / column / description
      Previous value: -"The price column to use, e.g. 'Close' or 'Adj Close'."New value: +"The price column to use, e.g. 'Close' or 'Adj Close'; for get_factor_analysis the output of a metric with several, e.g. 'Signal Line'. Leave unset to use the default of the indicator you selected. Defaults are 'Return' for get_best_fitting_copula, get_component_value_at_risk, get_copula_parameters, get_copula_simulation, get_covar, get_marginal_value_at_risk, get_tail_dependence_coefficient; None for get_factor_analysis."
    • removedInput schema / properties / column / type
      Removed value: -"string"
    • addedInput schema / properties / detail
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "get_factor_analysis only: 'information_coefficient', 'quantile_returns', 'quantile_turnover' or 'rank_autocorrelation' returns that part for a single metric instead of the summary."
      +}
    • addedInput schema / properties / horizons
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "items": {
      +        "type": "integer"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The number of periods the forward returns cover."
      +}
    • changedInput schema / properties / indicator / enum
      Previous value: -[
      -  "get_acerbi_szekely_test",
      -  "get_amihud_illiquidity",
      -  "get_autocorrelation",
      -  "get_best_fitting_copula",
      -  "get_coefficient_of_variation",
      -  "get_component_value_at_risk",
      -  "get_conditional_drawdown_at_risk",
      -  "get_conditional_value_at_risk",
      -  "get_copula_parameters",
      -  "get_copula_simulation",
      -  "get_covar",
      -  "get_downside_deviation",
      -  "get_entropic_value_at_risk",
      -  "get_ewma_volatility",
      -  "get_excess_volatility",
      -  "get_garch",
      -  "get_garch_forecast",
      -  "get_garch_parameters",
      -  "get_gjr_garch",
      -  "get_gjr_garch_forecast",
      -  "get_gjr_garch_parameters",
      -  "get_har_rv_forecast",
      -  "get_hill_estimator",
      -  "get_hurst_exponent",
      -  "get_kurtosis",
      -  "get_marginal_value_at_risk",
      -  "get_maximum_drawdown",
      -  "get_maximum_drawdown_duration",
      -  "get_maximum_drawdown_recovery_time",
      -  "get_mean_absolute_deviation",
      -  "get_roll_spread",
      -  "get_skewness",
      -  "get_tail_dependence_coefficient",
      -  "get_tail_ratio",
      -  "get_ulcer_index",
      -  "get_value_at_risk",
      -  "get_var_backtest",
      -  "get_variance",
      -  "get_volatility"
      -]New value: +[
      +  "get_acerbi_szekely_test",
      +  "get_amihud_illiquidity",
      +  "get_autocorrelation",
      +  "get_best_fitting_copula",
      +  "get_coefficient_of_variation",
      +  "get_component_value_at_risk",
      +  "get_conditional_drawdown_at_risk",
      +  "get_conditional_value_at_risk",
      +  "get_copula_parameters",
      +  "get_copula_simulation",
      +  "get_covar",
      +  "get_downside_deviation",
      +  "get_drawdown_series",
      +  "get_drawdown_table",
      +  "get_entropic_value_at_risk",
      +  "get_ewma_volatility",
      +  "get_excess_volatility",
      +  "get_factor_analysis",
      +  "get_garch",
      +  "get_garch_forecast",
      +  "get_garch_parameters",
      +  "get_gjr_garch",
      +  "get_gjr_garch_forecast",
      +  "get_gjr_garch_parameters",
      +  "get_har_rv_forecast",
      +  "get_hill_estimator",
      +  "get_hurst_exponent",
      +  "get_kurtosis",
      +  "get_marginal_value_at_risk",
      +  "get_maximum_drawdown",
      +  "get_maximum_drawdown_duration",
      +  "get_maximum_drawdown_recovery_time",
      +  "get_mean_absolute_deviation",
      +  "get_move_significance",
      +  "get_roll_spread",
      +  "get_skewness",
      +  "get_tail_dependence_coefficient",
      +  "get_tail_ratio",
      +  "get_ulcer_index",
      +  "get_value_at_risk",
      +  "get_var_backtest",
      +  "get_variance",
      +  "get_volatility"
      +]
    • changedInput schema / properties / limit / description
      Previous value: -"The rows to return, like head and tail: 5 for the first five, -5 for the last five (the most recent of a time series). A table with its periods as columns (financial statements, ratios) keeps its first or last periods instead. For ETF holdings the largest (or, negative, the smallest) by weight, and for a list (e.g. news or a screener) its length. 0 returns every row."New value: +"The rows to return, like head and tail: 5 for the first five, -5 for the last five (the most recent of a time series). A table with its periods as columns (financial statements, ratios) keeps its first or last periods instead, and rows per ticker (an earnings calendar) are selected per ticker. For ETF holdings the largest (or, negative, the smallest) by weight, and for a list (e.g. news or a screener) its length. 0 returns every row."
    • addedInput schema / properties / metrics
      Added value: +{
      +  "default": "anomalies",
      +  "description": "get_factor_analysis only: the metric(s) to analyse, a method name such as 'get_price_to_earnings_ratio', a comma-separated list, or a collection of the tool (see the tool description), e.g. 'profitability'.",
      +  "type": "string"
      +}
    • changedInput schema / properties / period / description
      Previous value: -"Observation frequency, e.g. 'daily', 'weekly', 'monthly', 'quarterly', or 'annual' (supported values differ per method)."New value: +"Observation frequency, e.g. 'daily', 'weekly', 'monthly', 'quarterly', or 'annual' (supported values differ per method). Leave unset to use the default of the indicator you selected. Defaults differ between indicators."
    • addedInput schema / properties / periods_apart
      Added value: +{
      +  "default": 1,
      +  "description": "The number of periods between the dates the quantile turnover and the rank autocorrelation compare.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / quantiles
      Added value: +{
      +  "default": 5,
      +  "description": "The number of quantiles the tickers are sorted into per period.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / recovery
      Added value: +{
      +  "default": false,
      +  "description": "Whether to return the gain needed to get back to the running peak (Recovery Needed) instead of the drawdown.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / top
      Added value: +{
      +  "default": 5,
      +  "description": "The number of drawdowns per asset, deepest first.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / window
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The number of periods the indicator looks back over, e.g. 14 or 20."
      +}
  4. Changed6 schema fields changedv2.3.1
    • changedInput schema / properties / benchmark_ticker / description
      Previous value: -"Ticker used as the market benchmark, e.g. 'SPY' or '^GSPC'."New value: +"Ticker used as the market benchmark, e.g. 'SPY' or '^GSPC'; 'None' for no benchmark."
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-10-27"New value: +""
    • changedInput schema / properties / end_date / description
      Previous value: -"End of the date range in YYYY-MM-DD format."New value: +"End of the date range in YYYY-MM-DD format; left empty, today (or the indicator's own window)."
    • changedInput schema / properties / limit / description
      Previous value: -"The rows to return, like head and tail: 5 for the first five, -5 for the last five (the most recent of a time series). A table with its periods as columns (financial statements, ratios) keeps its first or last periods instead. For ETF holdings the largest (or, negative, the smallest) by weight, and for a list (e.g. news or a screener) its length."New value: +"The rows to return, like head and tail: 5 for the first five, -5 for the last five (the most recent of a time series). A table with its periods as columns (financial statements, ratios) keeps its first or last periods instead. For ETF holdings the largest (or, negative, the smallest) by weight, and for a list (e.g. news or a screener) its length. 0 returns every row."
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-10-28"New value: +""
    • changedInput schema / properties / start_date / description
      Previous value: -"Start of the date range in YYYY-MM-DD format."New value: +"Start of the date range in YYYY-MM-DD format; left empty, five years before today (or the indicator's own window)."
  5. Changed6 schema fields changedv2.3.0
    • changedInput schema / properties / alpha / description
      Previous value: -"The confidence level (e.g., 0.05 for 95% confidence)."New value: +"The tail probability (e.g., 0.05 for the 95% confidence level)."
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-10-14"New value: +"2026-10-27"
    • changedInput schema / properties / k / description
      Previous value: -"The number of upper order statistics to use. If a float in (0, 1) it is interpreted as the fraction of the strictly positive observations to use."New value: +"The number of upper order statistics to use. If a float in (0, 1) it is interpreted as the fraction of the strictly positive observations to use. A period without such observations reports NaN with 0 observations used."
    • changedInput schema / properties / max_lag / description
      Previous value: -"The maximum lag to use when estimating the exponent."New value: +"The maximum lag, included, to use when estimating the exponent: the regression runs over the lags 2 up to and including `max_lag`."
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-10-15"New value: +"2021-10-28"
    • changedInput schema / properties / weights / description
      Previous value: -"The portfolio weight per ticker as an object, e.g. {'AAPL': 0.6, 'MSFT': 0.4}; equal weights when left unset."New value: +"Portfolio weights keyed by ticker. Normalized internally to sum to 1."
  6. Changed98 schema fields changedv2.2.3
    • changedInput schema / properties / alpha / description
      Previous value: -"Value for alpha."New value: +"The confidence level (e.g., 0.05 for 95% confidence)."
    • removedInput schema / properties / alpha / title
      Removed value: -"Alpha"
    • removedInput schema / properties / benchmark_ticker / title
      Removed value: -"Benchmark Ticker"
    • changedInput schema / properties / column / description
      Previous value: -"Value for column."New value: +"The price column to use, e.g. 'Close' or 'Adj Close'."
    • removedInput schema / properties / column / title
      Removed value: -"Column"
    • changedInput schema / properties / conditioning_ticker / description
      Previous value: -"Value for conditioning_ticker. Leave unset to use the default of the indicator you selected. Required by: get_covar."New value: +"The asset (or e.g. a benchmark/index) whose distress `ticker` is conditioned on. Leave unset to use the default of the indicator you selected. Required by: get_covar."
    • removedInput schema / properties / conditioning_ticker / title
      Removed value: -"Conditioning Ticker"
    • changedInput schema / properties / copula / description
      Previous value: -"Value for copula."New value: +"For get_copula_parameters: The copula family to fit, one of \"gaussian\", \"student-t\", \"clayton\", \"gumbel\" or \"frank\". For get_copula_simulation: The copula family to fit and simulate from, one of \"gaussian\", \"student-t\", \"clayton\", \"gumbel\" or \"frank\"."
    • removedInput schema / properties / copula / title
      Removed value: -"Copula"
    • changedInput schema / properties / distribution / description
      Previous value: -"Value for distribution."New value: +"The distribution to use for the rolling VaR estimates, one of \"historic\", \"gaussian\", \"studentt\" or \"evt\"."
    • removedInput schema / properties / distribution / title
      Removed value: -"Distribution"
    • changedInput schema / properties / dof / description
      Previous value: -"Value for dof."New value: +"The degrees of freedom of the Student-T copula, only used when `method=\"student-t\"`."
    • removedInput schema / properties / dof / title
      Removed value: -"Dof"
    • changedInput schema / properties / empirical_margins / description
      Previous value: -"Value for empirical_margins."New value: +"Whether to map the simulated pseudo-observations back to realistic returns via each asset's own empirical (historical) quantile function. When False, the raw pseudo-observations (each in (0, 1)) are returned instead."
    • removedInput schema / properties / empirical_margins / title
      Removed value: -"Empirical Margins"
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-10-02"New value: +"2026-10-14"
    • removedInput schema / properties / end_date / title
      Removed value: -"End Date"
    • changedInput schema / properties / estimator / description
      Previous value: -"Value for estimator."New value: +"How to construct the daily Realized Variance input, one of \"squared_return\", \"parkinson\", \"garman_klass\" or \"rogers_satchell\"."
    • removedInput schema / properties / estimator / title
      Removed value: -"Estimator"
    • changedInput schema / properties / fisher / description
      Previous value: -"Value for fisher."New value: +"Whether to use Fisher's definition of kurtosis (kurtosis = 0.0 for a normal distribution)."
    • removedInput schema / properties / fisher / title
      Removed value: -"Fisher"
    • removedInput schema / properties / growth / title
      Removed value: -"Growth"
    • changedInput schema / properties / horizon / description
      Previous value: -"Value for horizon."New value: +"The number of days ahead to forecast."
    • removedInput schema / properties / horizon / title
      Removed value: -"Horizon"
    • changedInput schema / properties / indicator / description
      Previous value: -"Name of the specific metric to calculate, e.g. 'get_asset_turnover_ratio'. Required — omitting it returns the list of available indicators."New value: +"Name of the specific metric to calculate, one of the listed values. Required — search_metrics finds the indicator (and its tool) for a metric by name."
    • changedInput schema / properties / indicator / enum
      Previous value: -[
      -  "get_acerbi_szekely_test",
      -  "get_amihud_illiquidity",
      -  "get_autocorrelation",
      -  "get_best_fitting_copula",
      -  "get_coefficient_of_variation",
      -  "get_component_value_at_risk",
      -  "get_conditional_drawdown_at_risk",
      -  "get_conditional_value_at_risk",
      -  "get_copula_parameters",
      -  "get_copula_simulation",
      -  "get_covar",
      -  "get_downside_deviation",
      -  "get_egarch",
      -  "get_egarch_forecast",
      -  "get_egarch_parameters",
      -  "get_entropic_value_at_risk",
      -  "get_ewma_volatility",
      -  "get_excess_volatility",
      -  "get_garch",
      -  "get_garch_forecast",
      -  "get_garch_parameters",
      -  "get_gjr_garch",
      -  "get_gjr_garch_forecast",
      -  "get_gjr_garch_parameters",
      -  "get_har_rv_forecast",
      -  "get_hill_estimator",
      -  "get_hurst_exponent",
      -  "get_kurtosis",
      -  "get_marginal_value_at_risk",
      -  "get_maximum_drawdown",
      -  "get_maximum_drawdown_duration",
      -  "get_maximum_drawdown_recovery_time",
      -  "get_mean_absolute_deviation",
      -  "get_roll_spread",
      -  "get_skewness",
      -  "get_tail_dependence_coefficient",
      -  "get_tail_ratio",
      -  "get_ulcer_index",
      -  "get_value_at_risk",
      -  "get_var_backtest",
      -  "get_variance",
      -  "get_volatility"
      -]New value: +[
      +  "get_acerbi_szekely_test",
      +  "get_amihud_illiquidity",
      +  "get_autocorrelation",
      +  "get_best_fitting_copula",
      +  "get_coefficient_of_variation",
      +  "get_component_value_at_risk",
      +  "get_conditional_drawdown_at_risk",
      +  "get_conditional_value_at_risk",
      +  "get_copula_parameters",
      +  "get_copula_simulation",
      +  "get_covar",
      +  "get_downside_deviation",
      +  "get_entropic_value_at_risk",
      +  "get_ewma_volatility",
      +  "get_excess_volatility",
      +  "get_garch",
      +  "get_garch_forecast",
      +  "get_garch_parameters",
      +  "get_gjr_garch",
      +  "get_gjr_garch_forecast",
      +  "get_gjr_garch_parameters",
      +  "get_har_rv_forecast",
      +  "get_hill_estimator",
      +  "get_hurst_exponent",
      +  "get_kurtosis",
      +  "get_marginal_value_at_risk",
      +  "get_maximum_drawdown",
      +  "get_maximum_drawdown_duration",
      +  "get_maximum_drawdown_recovery_time",
      +  "get_mean_absolute_deviation",
      +  "get_roll_spread",
      +  "get_skewness",
      +  "get_tail_dependence_coefficient",
      +  "get_tail_ratio",
      +  "get_ulcer_index",
      +  "get_value_at_risk",
      +  "get_var_backtest",
      +  "get_variance",
      +  "get_volatility"
      +]
    • removedInput schema / properties / indicator / title
      Removed value: -"Indicator"
    • changedInput schema / properties / k / description
      Previous value: -"Value for k."New value: +"The number of upper order statistics to use. If a float in (0, 1) it is interpreted as the fraction of the strictly positive observations to use."
    • removedInput schema / properties / k / title
      Removed value: -"K"
    • addedInput schema / properties / lag / anyOf
      Added value: +[
      +  {
      +    "type": "integer"
      +  },
      +  {
      +    "items": {
      +      "type": "integer"
      +    },
      +    "type": "array"
      +  }
      +]
    • removedInput schema / properties / lag / title
      Removed value: -"Lag"
    • removedInput schema / properties / lag / type
      Removed value: -"integer"
    • changedInput schema / properties / lags / description
      Previous value: -"Value for lags."New value: +"The number of lags (past periods) the test or model uses, e.g. 1 or 5."
    • removedInput schema / properties / lags / title
      Removed value: -"Lags"
    • changedInput schema / properties / lambda_ / description
      Previous value: -"Value for lambda_."New value: +"The decay factor. Higher values weight the past more heavily (slower to react), lower values weight recent returns more heavily (faster to react). RiskMetrics uses 0.94 for daily data."
    • removedInput schema / properties / lambda_ / title
      Removed value: -"Lambda"
    • addedInput schema / properties / limit
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The rows to return, like head and tail: 5 for the first five, -5 for the last five (the most recent of a time series). A table with its periods as columns (financial statements, ratios) keeps its first or last periods instead. For ETF holdings the largest (or, negative, the smallest) by weight, and for a list (e.g. news or a screener) its length."
      +}
    • changedInput schema / properties / max_lag / description
      Previous value: -"Value for max_lag."New value: +"The maximum lag to use when estimating the exponent."
    • removedInput schema / properties / max_lag / title
      Removed value: -"Max Lag"
    • changedInput schema / properties / method / description
      Previous value: -"Value for method. Leave unset to use the default of the indicator you selected. Defaults are 'close_to_close' for get_volatility; 'empirical' for get_tail_dependence_coefficient."New value: +"For get_tail_dependence_coefficient: The estimation method, one of \"empirical\", \"gaussian\" or \"student-t\". For get_volatility: Which Volatility estimator to use, one of \"close_to_close\", \"parkinson\", \"garman_klass\", \"rogers_satchell\" or \"yang_zhang\". Leave unset to use the default of the indicator you selected. Defaults are 'close_to_close' for get_volatility; 'empirical' for get_tail_dependence_coefficient."
    • removedInput schema / properties / method / title
      Removed value: -"Method"
    • removedInput schema / properties / minimum_acceptable_return / title
      Removed value: -"Minimum Acceptable Return"
    • changedInput schema / properties / monthly_window / description
      Previous value: -"Value for monthly_window."New value: +"The trailing window (in trading days) for the monthly RV component."
    • removedInput schema / properties / monthly_window / title
      Removed value: -"Monthly Window"
    • changedInput schema / properties / n_bootstrap / description
      Previous value: -"Value for n_bootstrap."New value: +"The number of bootstrap resamples used to estimate the Standard Error of Z2."
    • removedInput schema / properties / n_bootstrap / title
      Removed value: -"N Bootstrap"
    • addedInput schema / properties / n_simulations / anyOf
      Added value: +[
      +  {
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / n_simulations / default
      Previous value: -10000New value: +null
    • changedInput schema / properties / n_simulations / description
      Previous value: -"Value for n_simulations."New value: +"The number of joint draws to simulate. Leave unset to use the default of the indicator you selected. Defaults are 100 for get_copula_simulation."
    • removedInput schema / properties / n_simulations / title
      Removed value: -"N Simulations"
    • removedInput schema / properties / n_simulations / type
      Removed value: -"integer"
    • changedInput schema / properties / optimization_t / description
      Previous value: -"Value for optimization_t."New value: +"For get_garch: Time steps to optimize GARCH for. It is only used if no weights are given. For get_garch_parameters, get_gjr_garch_parameters: Time steps of the returns series to use for the optimization. For get_gjr_garch: Time steps to optimize GJR-GARCH for. It is only used if no weights are given."
    • removedInput schema / properties / optimization_t / title
      Removed value: -"Optimization T"
    • changedInput schema / properties / period / description
      Previous value: -"Observation frequency, e.g. 'monthly', 'quarterly', or 'annual'."New value: +"Observation frequency, e.g. 'daily', 'weekly', 'monthly', 'quarterly', or 'annual' (supported values differ per method)."
    • removedInput schema / properties / period / title
      Removed value: -"Period"
    • changedInput schema / properties / q / description
      Previous value: -"Value for q."New value: +"The threshold quantile used for the \"empirical\" method, in (0.5, 1)."
    • removedInput schema / properties / q / title
      Removed value: -"Q"
    • removedInput schema / properties / quarterly / title
      Removed value: -"Quarterly"
    • changedInput schema / properties / random_state / description
      Previous value: -"Value for random_state."New value: +"For get_acerbi_szekely_test: The seed for the bootstrap random number generator. For get_copula_simulation: The seed for the random number generator."
    • removedInput schema / properties / random_state / title
      Removed value: -"Random State"
    • removedInput schema / properties / rolling / title
      Removed value: -"Rolling"
    • addedInput schema / properties / scale / anyOf
      Added value: +[
      +  {
      +    "type": "number"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / scale / default
      Previous value: -1000000New value: +null
    • changedInput schema / properties / scale / description
      Previous value: -"Value for scale."New value: +"A multiplier applied to the resulting ratio purely for readability. Leave unset to use the default of the indicator you selected. Defaults are 1000000000 for get_amihud_illiquidity."
    • removedInput schema / properties / scale / title
      Removed value: -"Scale"
    • removedInput schema / properties / scale / type
      Removed value: -"number"
    • removedInput schema / properties / show_columns / title
      Removed value: -"Show Columns"
    • changedInput schema / properties / show_full_results / description
      Previous value: -"Value for show_full_results."New value: +"Only relevant when neither ticker is given. When False (the default), returns a square ticker-by-ticker grid of just the winning copula family per pair. When True, returns one row per pair instead, with the winning family's fitted parameter(s), Lower and Upper Tail Dependence, Log-Likelihood,..."
    • removedInput schema / properties / show_full_results / title
      Removed value: -"Show Full Results"
    • removedInput schema / properties / standardize / title
      Removed value: -"Standardize"
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-10-03"New value: +"2021-10-15"
    • removedInput schema / properties / start_date / title
      Removed value: -"Start Date"
    • changedInput schema / properties / tail / description
      Previous value: -"Value for tail."New value: +"Which tail to estimate, one of \"left\" (the loss tail) or \"right\" (the gain tail)."
    • removedInput schema / properties / tail / title
      Removed value: -"Tail"
    • changedInput schema / properties / test / description
      Previous value: -"Value for test."New value: +"Which test(s) to run, one of \"kupiec\", \"christoffersen\" or \"both\"."
    • removedInput schema / properties / test / title
      Removed value: -"Test"
    • removedInput schema / properties / threshold_percentile / title
      Removed value: -"Threshold Percentile"
    • changedInput schema / properties / ticker / description
      Previous value: -"Value for ticker. Leave unset to use the default of the indicator you selected. Required by: get_covar."New value: +"The asset whose conditional VaR is being measured. Leave unset to use the default of the indicator you selected. Required by: get_covar."
    • removedInput schema / properties / ticker / title
      Removed value: -"Ticker"
    • changedInput schema / properties / ticker_a / description
      Previous value: -"Value for ticker_a. Leave unset to use the default of the indicator you selected. Required by: get_tail_dependence_coefficient. Defaults are None for get_best_fitting_copula, get_copula_parameters, get_copula_simulation."New value: +"The first asset. Leave unset to use the default of the indicator you selected. Required by: get_tail_dependence_coefficient. Defaults are None for get_best_fitting_copula, get_copula_parameters, get_copula_simulation."
    • removedInput schema / properties / ticker_a / title
      Removed value: -"Ticker A"
    • changedInput schema / properties / ticker_b / description
      Previous value: -"Value for ticker_b. Leave unset to use the default of the indicator you selected. Required by: get_tail_dependence_coefficient. Defaults are None for get_best_fitting_copula, get_copula_parameters, get_copula_simulation."New value: +"The second asset. Leave unset to use the default of the indicator you selected. Required by: get_tail_dependence_coefficient. Defaults are None for get_best_fitting_copula, get_copula_parameters, get_copula_simulation."
    • removedInput schema / properties / ticker_b / title
      Removed value: -"Ticker B"
    • addedInput schema / properties / tickers / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "type": "string"
      +    },
      +    "type": "array"
      +  }
      +]
    • removedInput schema / properties / tickers / title
      Removed value: -"Tickers"
    • removedInput schema / properties / tickers / type
      Removed value: -"string"
    • changedInput schema / properties / time_steps / description
      Previous value: -"Value for time_steps. Leave unset to use the default of the indicator you selected. Defaults are 10 for get_egarch_forecast, get_garch_forecast, get_gjr_garch_forecast; None for get_egarch, get_garch, get_gjr_garch."New value: +"Time steps to calculate GARCH for. Leave unset to use the default of the indicator you selected. Defaults are 10 for get_garch_forecast, get_gjr_garch_forecast; None for get_garch, get_gjr_garch."
    • removedInput schema / properties / time_steps / title
      Removed value: -"Time Steps"
    • changedInput schema / properties / weekly_window / description
      Previous value: -"Value for weekly_window."New value: +"The trailing window (in trading days) for the weekly RV component."
    • removedInput schema / properties / weekly_window / title
      Removed value: -"Weekly Window"
    • changedInput schema / properties / weights / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": {
      +      "type": "number"
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / weights / description
      Previous value: -"Value for weights."New value: +"The portfolio weight per ticker as an object, e.g. {'AAPL': 0.6, 'MSFT': 0.4}; equal weights when left unset."
    • removedInput schema / properties / weights / title
      Removed value: -"Weights"
    • changedInput schema / properties / window_size / description
      Previous value: -"Value for window_size."New value: +"For get_acerbi_szekely_test: The rolling window size (in number of return observations) used to estimate each VaR/CVaR value. For get_var_backtest: The rolling window size (in number of return observations) used to estimate each VaR value."
    • removedInput schema / properties / window_size / title
      Removed value: -"Window Size"
    • changedInput schema / properties / within_period / description
      Previous value: -"Value for within_period."New value: +"Whether to calculate GJR-GARCH within each specified period or all at once."
    • removedInput schema / properties / within_period / title
      Removed value: -"Within Period"
    • removedInput schema / title
      Removed value: -"riskArguments"
  7. Changed6 schema fields changedv2.2.1
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-08-19"New value: +"2026-10-02"
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-08-20"New value: +"2021-10-03"
    • removedInput schema / properties / within_period / anyOf
      Removed value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • changedInput schema / properties / within_period / default
      Previous value: -nullNew value: +false
    • changedInput schema / properties / within_period / description
      Previous value: -"Value for within_period. Leave unset to use the default of the indicator you selected. Defaults differ between indicators."New value: +"Value for within_period."
    • addedInput schema / properties / within_period / type
      Added value: +"boolean"
  8. Changed33 schema fields changedv2.2.0
    • addedInput schema / properties / column
      Added value: +{
      +  "default": "Return",
      +  "description": "Value for column.",
      +  "title": "Column",
      +  "type": "string"
      +}
    • addedInput schema / properties / conditioning_ticker
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Value for conditioning_ticker. Leave unset to use the default of the indicator you selected. Required by: get_covar.",
      +  "title": "Conditioning Ticker"
      +}
    • addedInput schema / properties / copula
      Added value: +{
      +  "default": "gaussian",
      +  "description": "Value for copula.",
      +  "title": "Copula",
      +  "type": "string"
      +}
    • addedInput schema / properties / dof
      Added value: +{
      +  "default": 4,
      +  "description": "Value for dof.",
      +  "title": "Dof",
      +  "type": "number"
      +}
    • addedInput schema / properties / empirical_margins
      Added value: +{
      +  "default": true,
      +  "description": "Value for empirical_margins.",
      +  "title": "Empirical Margins",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-07-14"New value: +"2026-08-19"
    • addedInput schema / properties / estimator
      Added value: +{
      +  "default": "squared_return",
      +  "description": "Value for estimator.",
      +  "title": "Estimator",
      +  "type": "string"
      +}
    • addedInput schema / properties / horizon
      Added value: +{
      +  "default": 1,
      +  "description": "Value for horizon.",
      +  "title": "Horizon",
      +  "type": "integer"
      +}
    • changedInput schema / properties / indicator / enum
      Previous value: -[
      -  "get_autocorrelation",
      -  "get_coefficient_of_variation",
      -  "get_conditional_drawdown_at_risk",
      -  "get_conditional_value_at_risk",
      -  "get_downside_deviation",
      -  "get_entropic_value_at_risk",
      -  "get_ewma_volatility",
      -  "get_excess_volatility",
      -  "get_garch",
      -  "get_garch_forecast",
      -  "get_hurst_exponent",
      -  "get_kurtosis",
      -  "get_maximum_drawdown",
      -  "get_maximum_drawdown_duration",
      -  "get_maximum_drawdown_recovery_time",
      -  "get_mean_absolute_deviation",
      -  "get_skewness",
      -  "get_tail_ratio",
      -  "get_ulcer_index",
      -  "get_value_at_risk",
      -  "get_variance",
      -  "get_volatility"
      -]New value: +[
      +  "get_acerbi_szekely_test",
      +  "get_amihud_illiquidity",
      +  "get_autocorrelation",
      +  "get_best_fitting_copula",
      +  "get_coefficient_of_variation",
      +  "get_component_value_at_risk",
      +  "get_conditional_drawdown_at_risk",
      +  "get_conditional_value_at_risk",
      +  "get_copula_parameters",
      +  "get_copula_simulation",
      +  "get_covar",
      +  "get_downside_deviation",
      +  "get_egarch",
      +  "get_egarch_forecast",
      +  "get_egarch_parameters",
      +  "get_entropic_value_at_risk",
      +  "get_ewma_volatility",
      +  "get_excess_volatility",
      +  "get_garch",
      +  "get_garch_forecast",
      +  "get_garch_parameters",
      +  "get_gjr_garch",
      +  "get_gjr_garch_forecast",
      +  "get_gjr_garch_parameters",
      +  "get_har_rv_forecast",
      +  "get_hill_estimator",
      +  "get_hurst_exponent",
      +  "get_kurtosis",
      +  "get_marginal_value_at_risk",
      +  "get_maximum_drawdown",
      +  "get_maximum_drawdown_duration",
      +  "get_maximum_drawdown_recovery_time",
      +  "get_mean_absolute_deviation",
      +  "get_roll_spread",
      +  "get_skewness",
      +  "get_tail_dependence_coefficient",
      +  "get_tail_ratio",
      +  "get_ulcer_index",
      +  "get_value_at_risk",
      +  "get_var_backtest",
      +  "get_variance",
      +  "get_volatility"
      +]
    • addedInput schema / properties / k
      Added value: +{
      +  "default": 0.1,
      +  "description": "Value for k.",
      +  "title": "K",
      +  "type": "number"
      +}
    • addedInput schema / properties / method
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Value for method. Leave unset to use the default of the indicator you selected. Defaults are 'close_to_close' for get_volatility; 'empirical' for get_tail_dependence_coefficient.",
      +  "title": "Method"
      +}
    • addedInput schema / properties / monthly_window
      Added value: +{
      +  "default": 22,
      +  "description": "Value for monthly_window.",
      +  "title": "Monthly Window",
      +  "type": "integer"
      +}
    • addedInput schema / properties / n_bootstrap
      Added value: +{
      +  "default": 1000,
      +  "description": "Value for n_bootstrap.",
      +  "title": "N Bootstrap",
      +  "type": "integer"
      +}
    • addedInput schema / properties / n_simulations
      Added value: +{
      +  "default": 10000,
      +  "description": "Value for n_simulations.",
      +  "title": "N Simulations",
      +  "type": "integer"
      +}
    • addedInput schema / properties / q
      Added value: +{
      +  "default": 0.95,
      +  "description": "Value for q.",
      +  "title": "Q",
      +  "type": "number"
      +}
    • addedInput schema / properties / random_state
      Added value: +{
      +  "default": 42,
      +  "description": "Value for random_state.",
      +  "title": "Random State",
      +  "type": "integer"
      +}
    • changedInput schema / properties / rolling / description
      Previous value: -"Rolling window size in number of periods. When set, the metric is computed over a smoothly overlapping trailing window across the full history (e.g. period='monthly' and rolling=6 gives a rolling 6-month value) instead of one value per period, or (for economics indicators) a simple moving average used to smooth the raw series."New value: +"Rolling window size in number of periods. When set, the metric is computed over a smoothly overlapping trailing window across the full history (e.g. period='monthly' and rolling=6 gives a rolling 6-month value) instead of one value per period, or (for economics indicators) a simple moving average used to smooth the raw series. Leave unset to use the default of the indicator you selected. Defaults are None for get_conditional_drawdown_at_risk, get_conditional_value_at_risk, get_downside_deviation, get_excess_volatility, get_kurtosis, get_skewness, get_tail_ratio, get_value_at_risk, get_variance, get_volatility; 14 for get_ulcer_index."
    • addedInput schema / properties / scale
      Added value: +{
      +  "default": 1000000,
      +  "description": "Value for scale.",
      +  "title": "Scale",
      +  "type": "number"
      +}
    • addedInput schema / properties / show_full_results
      Added value: +{
      +  "default": false,
      +  "description": "Value for show_full_results.",
      +  "title": "Show Full Results",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-07-15"New value: +"2021-08-20"
    • addedInput schema / properties / tail
      Added value: +{
      +  "default": "left",
      +  "description": "Value for tail.",
      +  "title": "Tail",
      +  "type": "string"
      +}
    • addedInput schema / properties / test
      Added value: +{
      +  "default": "both",
      +  "description": "Value for test.",
      +  "title": "Test",
      +  "type": "string"
      +}
    • addedInput schema / properties / ticker
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Value for ticker. Leave unset to use the default of the indicator you selected. Required by: get_covar.",
      +  "title": "Ticker"
      +}
    • addedInput schema / properties / ticker_a
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Value for ticker_a. Leave unset to use the default of the indicator you selected. Required by: get_tail_dependence_coefficient. Defaults are None for get_best_fitting_copula, get_copula_parameters, get_copula_simulation.",
      +  "title": "Ticker A"
      +}
    • addedInput schema / properties / ticker_b
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Value for ticker_b. Leave unset to use the default of the indicator you selected. Required by: get_tail_dependence_coefficient. Defaults are None for get_best_fitting_copula, get_copula_parameters, get_copula_simulation.",
      +  "title": "Ticker B"
      +}
    • changedInput schema / properties / time_steps / description
      Previous value: -"Value for time_steps."New value: +"Value for time_steps. Leave unset to use the default of the indicator you selected. Defaults are 10 for get_egarch_forecast, get_garch_forecast, get_gjr_garch_forecast; None for get_egarch, get_garch, get_gjr_garch."
    • addedInput schema / properties / weekly_window
      Added value: +{
      +  "default": 5,
      +  "description": "Value for weekly_window.",
      +  "title": "Weekly Window",
      +  "type": "integer"
      +}
    • addedInput schema / properties / weights
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Value for weights.",
      +  "title": "Weights"
      +}
    • addedInput schema / properties / window_size
      Added value: +{
      +  "default": 252,
      +  "description": "Value for window_size.",
      +  "title": "Window Size",
      +  "type": "integer"
      +}
    • addedInput schema / properties / within_period / anyOf
      Added value: +[
      +  {
      +    "type": "boolean"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / within_period / default
      Previous value: -trueNew value: +null
    • changedInput schema / properties / within_period / description
      Previous value: -"Value for within_period."New value: +"Value for within_period. Leave unset to use the default of the indicator you selected. Defaults differ between indicators."
    • removedInput schema / properties / within_period / type
      Removed value: -"boolean"
  9. Changed13 schema fields changed
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-07-09"New value: +"2026-07-14"
    • changedInput schema / properties / indicator / enum
      Previous value: -[
      -  "get_conditional_value_at_risk",
      -  "get_entropic_value_at_risk",
      -  "get_garch",
      -  "get_garch_forecast",
      -  "get_kurtosis",
      -  "get_maximum_drawdown",
      -  "get_skewness",
      -  "get_ulcer_index",
      -  "get_value_at_risk"
      -]New value: +[
      +  "get_autocorrelation",
      +  "get_coefficient_of_variation",
      +  "get_conditional_drawdown_at_risk",
      +  "get_conditional_value_at_risk",
      +  "get_downside_deviation",
      +  "get_entropic_value_at_risk",
      +  "get_ewma_volatility",
      +  "get_excess_volatility",
      +  "get_garch",
      +  "get_garch_forecast",
      +  "get_hurst_exponent",
      +  "get_kurtosis",
      +  "get_maximum_drawdown",
      +  "get_maximum_drawdown_duration",
      +  "get_maximum_drawdown_recovery_time",
      +  "get_mean_absolute_deviation",
      +  "get_skewness",
      +  "get_tail_ratio",
      +  "get_ulcer_index",
      +  "get_value_at_risk",
      +  "get_variance",
      +  "get_volatility"
      +]
    • addedInput schema / properties / lags
      Added value: +{
      +  "default": 10,
      +  "description": "Value for lags.",
      +  "title": "Lags",
      +  "type": "integer"
      +}
    • addedInput schema / properties / lambda_
      Added value: +{
      +  "default": 0.94,
      +  "description": "Value for lambda_.",
      +  "title": "Lambda",
      +  "type": "number"
      +}
    • addedInput schema / properties / max_lag
      Added value: +{
      +  "default": 20,
      +  "description": "Value for max_lag.",
      +  "title": "Max Lag",
      +  "type": "integer"
      +}
    • addedInput schema / properties / minimum_acceptable_return
      Added value: +{
      +  "default": 0,
      +  "description": "The minimum acceptable return (MAR) threshold below which returns are considered downside, e.g. 0.0 for downside relative to a zero return.",
      +  "title": "Minimum Acceptable Return",
      +  "type": "number"
      +}
    • addedInput schema / properties / rolling / anyOf
      Added value: +[
      +  {
      +    "type": "integer"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / rolling / default
      Previous value: -14New value: +null
    • changedInput schema / properties / rolling / description
      Previous value: -"Value for rolling."New value: +"Rolling window size in number of periods. When set, the metric is computed over a smoothly overlapping trailing window across the full history (e.g. period='monthly' and rolling=6 gives a rolling 6-month value) instead of one value per period, or (for economics indicators) a simple moving average used to smooth the raw series."
    • removedInput schema / properties / rolling / type
      Removed value: -"integer"
    • addedInput schema / properties / standardize
      Added value: +{
      +  "default": false,
      +  "description": "Return the Z-Score (standard score) instead of the raw values, i.e. how many standard deviations each value is from the mean of its own series. When combined with growth=True, the growth values are standardized instead of the raw values.",
      +  "title": "Standardize",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-07-10"New value: +"2021-07-15"
    • addedInput schema / properties / threshold_percentile
      Added value: +{
      +  "default": 0.95,
      +  "description": "Only used when distribution='evt'. The percentile of losses above which the Generalized Pareto Distribution is fitted, e.g. 0.95 fits on the worst 5% of losses.",
      +  "title": "Threshold Percentile",
      +  "type": "number"
      +}
  10. Changed2 schema fields changedv2.1.4
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-06-27"New value: +"2026-07-09"
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-06-28"New value: +"2021-07-10"
  11. Changed2 schema fields changedv2.1.3
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-06-23"New value: +"2026-06-27"
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-06-24"New value: +"2021-06-28"
  12. Changed4 schema fields changedv0.1.2
    • changedInput schema / properties / end_date / default
      Previous value: -"2026-06-22"New value: +"2026-06-23"
    • removedInput schema / properties / rounding
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "integer"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "description": "Number of decimal places to round results to.",
      -  "title": "Rounding"
      -}
    • addedInput schema / properties / show_columns
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Comma-separated names to filter the output. For historical data use the key names visible in any response record (e.g. 'Close,Volume,Return'). For financial statements use the 'metric' field values from the response (e.g. 'Revenue,Net Income,EBITDA'). Call the tool once without this parameter to see all available names, then repeat with show_columns to reduce response size and token usage.",
      +  "title": "Show Columns"
      +}
    • changedInput schema / properties / start_date / default
      Previous value: -"2021-06-23"New value: +"2021-06-24"
  13. Addedv0.1.1

TDQS

B3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. Beyond that, the description supplies genuinely useful behavioural context: what the VaR Multiple means ('below -1 is a VaR exceedance'), how the IC should be read ('a negative IC for the volatility is the low-volatility anomaly'), the default Delta-CoVaR semantics of get_covar, and the 100-draw default of get_copula_simulation. It stops short of describing response shape or performance characteristics, which the output schema partly covers.

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

Conciseness2/5

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

The text is a single sprawling block of densely parenthesised sentences that mixes output semantics, parameter documentation and per-indicator defaults. It is not front-loaded around a clear hierarchy; a reader must wade through the drawdown parentheticals before reaching the indicator-specific notes that matter most.

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 tool dispatching 46 indicators, only a handful (copula simulation, tail dependence, covar, amihud, factor analysis, move significance, drawdown variants) receive any narrative treatment, while acerbi_szekely, hill_estimator, hurst_exponent, ulcer_index, har_rv_forecast, var_backtest and others appear only as enum values. The presence of an output schema and rich annotations offsets this somewhat, but the description is far from complete for the tool's complexity.

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% across 59 parameters, so the baseline is 3. The description does add interpretation for a subset — rolling=N spanning the full history, the 'anomalies'/'all' metric collections, detail= options, period defaults — but the majority of parameters (k, q, dof, tail, test, fisher, threshold_percentile, etc.) receive meaning only from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Pre-computed risk metrics' and then enumerates a large set of measures (VaR variants, CVaR, EVaR, GARCH volatility, drawdowns, CDaR, Tail Ratio, etc.), so the general purpose is inferable. However, this is a 46-value dispatcher tool and the description never states the organising principle that separates it from siblings like 'volatility', 'performance' or 'econometrics', so an agent cannot cleanly tell which family a given metric belongs to.

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?

There are concrete usage constraints: 'Requires tickers=AAPL', comma-separated tickers for multiple assets, 'Needs tickers= with at least ten, preferably twenty or more tickers' for factor analysis, and period/rolling combinations. What is missing is any when-to-use-this-vs-alternative guidance — nothing says to prefer the 'volatility' sibling for volatility work or how to choose between the many indicators beyond the required indicator= enum.

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