Skip to main content
Glama
tedorigawa001

TradingView-MCP

run_market_event_study

Run read-only market event studies on the active chart's closed OHLC bars testing breakout, retest, and exhaustion patterns; reports forward returns, MFE/MAE, timing, and confidence intervals.

Instructions

Run a bounded, read-only market event study on closed OHLC bars from the active chart. Condition session_auction classifies the first break of a prior local-session range as accepted outside closes or a failed return inside. Condition session_exhaustion_handoff tests whether a closed-bar prior-session direction fails to extend in an early handoff session and reverses; its outcomes begin only after the configured handoff window has fully closed. Condition event_aftershock_retest evaluates caller-supplied, canonical economic-event timestamps through a post-event initial range, close breakout, and first boundary retest. Condition failed_breakout evaluates a first sweep beyond a completed local-session range that closes back inside it, with optional opposite-direction confirmation closes. It returns directional forward returns, MFE, MAE, target timing, explicit exclusions, and optional non-overlapping time folds with bounded mean and rate confidence intervals. The caller can declare the number of configurations inspected; serial dependence and multiple testing are not silently adjusted. An optional regime split joins each event only to a price/volatility label whose bar closed before the signal bar began, and keeps sparse cells not evaluable. Signal-bar close is an event reference, not an assumed fill. It never ranks parameters, changes the chart, or places orders.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoMost recent loaded bars to inspect. Default: 5000; up to 30,000 after explicit history loading
foldsNo
regimeNoOptional point-in-time price/volatility regime split using only bars closed before each signal bar
journalNo
horizonsYes
conditionYes
event_limitNoMaximum per-event rows to return. Aggregate metrics always use all events. Default: 50
minimum_eventsYes
expected_symbolYes
confidence_levelNoConfidence level for normal-approximation mean and Wilson rate intervals. Default: 0.95
target_return_bpsYes
expected_timeframeYes
configuration_trialsNoTotal related parameter/configuration trials inspected so far, including this one

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses read-only semantics, closed-bar usage, the point-in-time regime join, the signal-bar-close-is-not-a-fill caveat, the lack of silent multiple-testing adjustment, and the absence of side effects such as ranking, chart changes, or order placement.

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?

The description is dense but each sentence earns its place, front-loading the core purpose and then covering condition semantics, outputs, statistical honesty, and side-effect limitations. It could benefit from bulleted structure given the number of distinct behavioral claims, but the length is justified for the tool's complexity.

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?

The description is strong for the aspects it covers, including return metrics, exclusions, confidence intervals, and regime behavior, but it omits two condition types present in the schema: fair_value_gap_retest and composite_condition. Given the high complexity and absence of an output schema, these omissions leave the description somewhat incomplete for full autonomous invocation.

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?

Despite low schema description coverage, the prose adds meaningful semantics to the most complex parameters: it explains each major condition type, the regime split's lookahead safety, non-overlapping time folds, and caller-declared configuration trials. It does not elaborate on simpler required parameters like horizons or target_return_bps, but those are reasonably inferable from their names and schema constraints.

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

Purpose4/5

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

The description opens with a specific verb and resource: 'Run a bounded, read-only market event study on closed OHLC bars from the active chart.' It clearly explains what the tool produces and enumerates several condition types, but it does not explicitly distinguish itself from related sibling studies such as run_event_study_falsification_audit.

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 conveys clear usage context by specifying that it operates on the active chart, is bounded and read-only, and never ranks parameters, changes the chart, or places orders. This helps the agent understand when to use it, though it does not explicitly name alternatives or state when-not-to-use conditions.

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

Install Server

Other Tools