Skip to main content
Glama

Ask a quant question

ask_quant
Idempotent

Answers a question about the numbers of named symbols, computed on Sortefi's market data, and shows how it was worked out. Covers US stocks, Indian NSE stocks, ETFs, forex pairs and crypto perpetual futures, on candles from 1 minute to monthly: total and yearly returns over any window; a lump sum or a monthly investment plan, with dividends; volatility, Sharpe, Sortino and Calmar ratios and value at risk; drawdowns, every crash and its recovery; beta, alpha and correlation against an index or another symbol; how often something happened and what followed, streaks, gaps and event studies; seasonality by weekday, month, hour or trading session; technical indicators, candlestick patterns and Renko bricks inside any statistic; statistical tests (stationarity, autocorrelation, cointegration, fitted distributions); backtests of a stated trading rule with costs, slippage, stops and targets, long or short, with a settings search and a look-ahead check; portfolios with stated or fitted weights; current fundamentals, US debt and cash history, ownership and US short interest; and options figures for Indian and crypto markets (implied volatility, put-call ratio, max pain, skew, and the payoff and Greeks of a stated strategy). Up to 8 symbols per question, or an index or group. Sortefi reads the question with its own rules and returns the answer, the tables behind it, the method, and a link to the saved answer. It reports what happened in the data — requests for advice, forecasts or trade setups are declined. For a list of symbols that match conditions, use run_screen instead. Runs on the user's Sortefi account: each completed answer is charged — a free prompt if the account has one left, otherwise wallet credits, at least 10 (1 credit = $0.01, or ₹1 on accounts topped up in rupees). The result states what was charged and the balance left. Follow-up questions and declines are free.

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": {
      "question": "<question>",
      "market": "<market>"
    },
    "name": "ask_quant"
  }
}

Input Schema

NameRequiredDescriptionDefault
marketYesUS_EQUITY = US stocks, INDIA_EQUITY = Indian NSE stocks, ETF = US-listed ETFs, FOREX = currency pairs, CRYPTO_PERPS = crypto perpetual futures (Binance, HyperLiquid).
questionYesThe question in the user's own words, with the symbols, period, timeframe and figures exactly as they stated them. When answering a Sortefi follow-up question: the original question followed by the user's answer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnly=false, idempotent=true, destructive=false; the description adds substantial context beyond that: it runs on the user's account, each completed answer is charged (free prompt or ≥10 credits at 1 credit = $0.01 / ₹1, balance reported), and follow-ups and declines are free. It also discloses the return shape (answer, backing tables, method, saved-answer link) and the interpretation caveats (Sortefi's own parsing rules, up to 8 symbols or an index/group).

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?

Purpose, sibling routing and pricing are front-loaded, and the long capability catalog is dense but earns its place by telling the agent which question types are answerable. The middle semicolon run-on is heavy, though every clause carries routing information rather than filler.

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

Completeness5/5

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

With no output schema, the description carries the burden of describing returns and does so (answer plus tables, method, link, and stated charge/balance). It also covers cost model, refusals, symbol limits and follow-up semantics, leaving little an agent needs to know before invoking.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is met; the description adds meaning the schema does not, notably the 8-symbol ceiling and the 'index or group' alternative. It reinforces that the question should carry the user's own symbols, period, timeframe and figures verbatim, which shapes how the agent should phrase input.

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

Purpose5/5

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

Opens with a specific verb and resource (answers a question about numbers of named symbols) and scopes the universe precisely: US stocks, NSE stocks, ETFs, forex pairs, crypto perps, 1-minute to monthly candles. It also distinguishes a single named-symbol quant answer from the sibling run_screen by name.

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

Usage Guidelines5/5

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

States explicitly when to route elsewhere ('For a list of symbols that match conditions, use run_screen instead') and when the tool refuses ('requests for advice, forecasts or trade setups are declined'). It also documents follow-up handling and free declines, so the agent knows the operating envelope.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources