\begin{table}[htbp] \centering \caption{Taxonomy of the tool catalogue exposed to the model. VQuant defines more than two hundred tools through a schema-driven function-calling protocol. Counts are approximate and group conceptually related endpoints; the financial families are backed by a market-data provider exposing over 265 endpoints, wrapped by roughly 230 typed server functions.} \label{tab:tools} \begin{threeparttable} \begin{tabular}{@{}lll@{}} \toprule Family & Count & Representative tools \\ \midrule Company fundamentals & 40+ & profile, income statement, balance sheet, cash flow, ratios \\ Market data & 30+ & quote, historical / intraday prices, market movers, batch quote \\ Technical analysis & 8+ & RSI, MACD, EMA/SMA, ADX, CCI, stochastic, Williams \%R \\ Analyst and ratings & 20+ & estimates, price targets, upgrades/downgrades, rating history \\ Insider and institutional & 15+ & insider trades, 13F filings, congressional/senate trading \\ Economic and macro & 15+ & treasury rates, indicators, calendar, COT reports \\ Forex and crypto & 15+ & FX and crypto quotes, lists, historical series, commodities \\ SEC and compliance & 25+ & filings by form type, company notes, call transcripts \\ Events and calendars & 10+ & earnings, dividends, splits, IPO calendar and disclosures \\ ESG and alternative & 20+ & ESG scores, social sentiment, headcount, executive pay \\ Options & 4 & option chain, prices, Greeks, volatility surface \\ Advanced analysis & 7 & Monte Carlo, Black--Scholes, custom Python, bulk download \\ Web research & 6 & scrape, crawl, extract; AI / semantic / engine search \\ \bottomrule \end{tabular} \begin{tablenotes}[flushleft] \footnotesize \item \textit{Notes.} The system prompt instructs the model to select tools according to query complexity (Section~\ref{subsec:routing}); the most powerful entries---Monte Carlo simulation, option pricing, and arbitrary Python execution---are described in detail in Section~\ref{sec:capabilities}. \end{tablenotes} \end{threeparttable} \end{table}