Skip to main content
Glama

VARRD — Statistically Validated Trading Edges + AI Research Engine

by io.github.augiemazza

varrd_ai

Talk to VARRD AI (~$0.25/turn). Describe any trading idea in plain language and the system handles everything — loading decades of market data, charting your pattern, running statistical tests, backtesting with stops, and generating exact trade setups.

MULTI-TURN: First call creates a session. Keep calling with the same session_id, following context.next_actions each time.

  1. Your idea -> VARRD charts pattern

  2. 'test it' -> statistical test (event study or backtest)

  3. 'show me the trade setup' -> exact entry/stop/target prices

HYPOTHESIS INTEGRITY (critical): VARRD tests ONE hypothesis at a time — one formula, one setup. Never combine multiple setups into one formula or ask to 'test all' — each idea must be tested as a separate hypothesis for the statistics to be valid. Say 'start a new hypothesis' between ideas to reset cleanly.

  • ALLOWED: Test the SAME setup across multiple markets ('test this on ES, NQ, and CL') — same formula, different data.

  • NOT ALLOWED: Test multiple DIFFERENT formulas/setups at once — each is a separate hypothesis requiring its own chart-test-result cycle. If ELROND council returns 4 setups, test each one separately: chart setup 1 -> test -> results -> 'start new hypothesis' -> chart setup 2 -> etc.

KEY CAPABILITIES you can ask for:

  • 'Use the ELROND council on [market]' -> 8 expert investigators

  • 'Optimize the stop loss and take profit' -> SL/TP grid search

  • 'Test this on ES, NQ, and CL' -> multi-market testing

  • 'Simulate trading this with 1.5 ATR stop' -> backtest with stops

EDGE VERDICTS in context.edge_verdict after testing:

  • STRONG EDGE: Significant vs zero AND vs market baseline

  • MARGINAL: Significant vs zero only (beats nothing, but real signal)

  • PINNED: Significant vs market only (flat returns but different from market)

  • NO EDGE: Neither significant test passed

TERMINAL STATES: Stop when context.has_edge is true (edge found) or false (no edge — valid result). Always read context.next_actions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageYesYour trading idea, research question, or instruction (e.g. 'test it', 'show trade setup').
session_idNoSession ID from a previous call. Omit to start a new research session.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
textNoAI response text
contextNoWorkflow state, edge verdict, next actions
widgetsNoChart, event study, backtest, or trade setup widgets
session_idNoSession ID for multi-turn conversation

TDQS

A4.7/5.0
Behavior5/5

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

Beyond annotations (readOnlyHint=false, openWorldHint=true), the description discloses cost (~$0.25/turn), the multi-turn session state, the 'ONE hypothesis at a time' constraint, edge verdict categories, and terminal states. This is rich behavioral context not captured in structured fields.

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?

Though lengthy, the description is sectioned logically (MULTI-TURN, HYPOTHESIS INTEGRITY, KEY CAPABILITIES, EDGE VERDICTS, TERMINAL STATES) and every sentence carries functional guidance for a complex tool. It is front-loaded with the core purpose and then details the workflow without fluff.

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?

For a complex multi-turn tool, the description covers the full lifecycle: session creation, hypothesis testing, allowed/not-allowed patterns, verdict interpretation, and stopping criteria. It references context fields (has_edge, next_actions, edge_verdict) and assumes an output schema, so the agent is fully equipped to use the tool correctly.

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%, but the description adds value by giving concrete message examples ('test it', 'show me the trade setup') and clarifying session_id behavior (omit to start new). This supports the schema without redundancy, though it doesn't define parameter constraints beyond what's already present.

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?

The description opens with a clear statement: "Talk to VARRD AI... Describe any trading idea in plain language and the system handles everything..." It enumerates specific capabilities (charting, statistical tests, backtesting, trade setups) and distinguishes from siblings by emphasizing interactive multi-turn research rather than autonomous execution.

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?

The description provides an explicit multi-turn protocol, including 'First call creates a session. Keep calling with the same session_id, following context.next_actions each time.' It also gives allowed/not-allowed examples for hypothesis testing, but doesn't explicitly reference sibling tools as alternatives, so it lacks explicit when-not/alternatives.

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

All VARRD — Statistically Validated Trading Edges + AI Research Engine toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation4/5

Most tools have distinct purposes, but 'autonomous_varrd_ai' and 'varrd_ai' could cause confusion despite clear descriptions. 'varrd_edges' vs 'varrd_ai' are distinct. Overall, minor overlap but manageable.

Naming Consistency3/5

Names mix snake_case verbs and noun phrases, and the 'varrd_' prefix is inconsistently applied. 'autonomous_varrd_ai' deviates from the verb_noun pattern. Still readable.

Tool Count5/5

9 tools is well-scoped for the server's purpose—covers research, credit management, results browsing, and session control without bloat.

Completeness4/5

Covers core workflows: hypothesis generation, testing, browsing live edges, and managing credits. Missing explicit update/delete capabilities for hypotheses, but overall surface is sufficient.

Resources