Skip to main content
Glama

veritas-8183-agent-notary-witness

audit_quant_backtest_escrow

Idempotent

[Private] Bought a trading strategy? Check its backtest for look-ahead bias, wrong PnL math, low profit factor or hidden drawdown before you pay. Example: minTrades=20, minProfitFactor=1.25.

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": {
      "trades": "<trades>"
    },
    "name": "audit_quant_backtest_escrow"
  }
}

Input Schema

NameRequiredDescriptionDefault
tradesYesArray of trade objects with entry/exit timestamps, prices, and PnL.
minTradesNoMinimum required trade count for statistical validity.
maxDrawdownPctNoMaximum allowed peak-to-trough equity drawdown percentage.
minProfitFactorNoMinimum gross profit to gross loss ratio.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / properties / maxDrawdownPct / description
      Added value: +"Maximum allowed peak-to-trough equity drawdown percentage."
    • addedInput schema / properties / minProfitFactor / description
      Added value: +"Minimum gross profit to gross loss ratio."
    • addedInput schema / properties / minTrades / description
      Added value: +"Minimum required trade count for statistical validity."
    • changedInput schema / properties / trades / description
      Previous value: -"Array of trades with entryTime/entryTimestampMs, exitTime/exitTimestampMs, side, entryPrice, exitPrice, size, pnlUsd"New value: +"Array of trade objects with entry/exit timestamps, prices, and PnL."
    • addedInput schema / properties / trades / items
      Added value: +{
      +  "type": "object"
      +}
  2. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is covered; the description adds that the analysis is '[Private]' and lists the specific checks performed. It does not disclose what the response contains (verdict, findings list, per-check scores) or how failures are reported, which is the main behavioral gap for an audit tool.

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

Conciseness5/5

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

Two tight sentences plus a compact example, with the framing question front-loaded and the defect list immediately after. Every clause carries information; nothing is padded or restated from the schema.

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

Completeness3/5

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

With four parameters and no output schema, the description should say what an audit returns — pass/fail per check, a findings report, or metrics — and it does not, leaving the agent unable to anticipate result shape or interpret failures. The input side is complete, since the schema fully documents the trades array and thresholds and the description supplies example values.

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 3, but the description goes further by giving concrete illustrative values (minTrades=20, minProfitFactor=1.25) that convey sensible threshold magnitudes and that the thresholds are caller-tunable guards. It adds nothing about maxDrawdownPct units, though the schema already labels that as a percentage.

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?

States a specific verb ('Check its backtest') and resource (a purchased trading strategy's backtest) and enumerates the exact defects audited: look-ahead bias, wrong PnL math, low profit factor, hidden drawdown. This clearly separates it from the sibling audit_*_escrow tools, which cover agents, inference, API SLAs, DePIN GPU, RAG embeddings and smart contracts rather than quant backtests.

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

Usage Guidelines4/5

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

Gives an explicit trigger — 'Bought a trading strategy? ... before you pay' — which tells the agent this is a pre-purchase due-diligence call. It offers no when-not guidance or named alternative, but the sibling audit tools are already disambiguated by domain.

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.