Skip to main content
Glama
tedorigawa001

TradingView-MCP

compute_feature_outcome_relationships

Measures point-in-time relationships between closed-bar price features and later returns on a TradingView chart, returning bucketed forward-return, upside, and downside distributions.

Instructions

Measure point-in-time relationships between selected closed-bar price features and later observed returns on one exact TradingView chart. It classifies ATR compression, candle body direction, wick imbalance, directional streaks, range position, and opening gaps using only the signal bar and prior OHLC. It returns bucketed forward-return, upside, downside, and fold distributions without optimizing thresholds, changing the chart, or making a trade recommendation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoMost recent loaded bars to inspect. Default: 5000
foldsNo
regimeNoOptional predeclared point-in-time market-regime filter for a limited feature hypothesis
journalNo
featuresNoPoint-in-time features to classify. Default: all six
horizonsYes
signal_toNoExclusive signal-bar timestamp for a fixed forward collection window
signal_fromNoInclusive signal-bar timestamp for a fixed forward collection window
atr_lookbackNo
range_lookbackNo
expected_symbolYes
confidence_levelNoConfidence level for normal-approximation mean and Wilson rate intervals. Default: 0.95
feature_selectionNoOne preregistered feature bucket. Cannot be combined with features.
gap_atr_thresholdNo
observation_limitNoMaximum labelled observations to return. Aggregates always use all rows. Default: 100
expected_timeframeYes
minimum_effect_bpsYesFrozen pre-registered candidacy floor in basis points. It must be stated and cannot be relaxed; significance alone reports existence, not size.
streak_minimum_barsNo
body_ratio_thresholdNo
configuration_trialsNoTotal related feature/threshold configurations inspected so far, including this one
minimum_observationsNo
range_position_lowerNo
range_position_upperNo
atr_baseline_lookbackNo
wick_imbalance_thresholdNo
atr_compression_low_ratioNo
atr_compression_high_ratioNo
empirical_null_calibrationNoRun the fixed 1,000-replication circular moving-block empirical-null calibration on the same closed bars. Default: false

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4/5.0
Behavior4/5

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

No annotations are present, so the description carries the full burden. It discloses data scope ('using only the signal bar and prior OHLC'), behavioral non-actions ('without optimizing thresholds, changing the chart, or making a trade recommendation'), and output shape ('bucketed forward-return, upside, downside, and fold distributions'). This is substantial behavioral disclosure that helps the agent predict side effects.

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?

Three sentences, front-loaded with the central purpose, then method, then output and exclusions. No redundancy; every sentence adds distinct information and the description is compact 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?

For a 28-parameter analysis tool with no output schema, the description gives a solid high-level summary of what it computes and returns. However, it omits invocation prerequisites (e.g., data must be loaded on the active chart), does not explain the 'fold' concept or the signal_from/to fixed-window behavior, and does not tie the description to the required parameters. Adequate for tool selection, not for full invocation guidance.

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

Parameters2/5

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

Schema description coverage is only 39%, so the description must compensate, but it does not fully. It does map the six feature enum values and hints at signal-bar/lookback semantics, yet it leaves the majority of the 28 parameters unexplained—including required minimum_effect_bps, signal_from/to, the regime object, configuration_trials, and observation_limit. This is meaningful but insufficient compensation for such a large parameter surface.

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 states a specific verb ('Measure'), resource ('relationships between selected closed-bar price features and later observed returns'), and tight constraints ('point-in-time', 'one exact TradingView chart'). It enumerates the six feature classes and adds negative scope ('without optimizing thresholds, changing the chart, or making a trade recommendation') that distinguishes it from related falsification and audit tools.

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?

Clear context is provided: use this tool to measure feature-outcome relationships on a single chart in a point-in-time, non-optimizing way. It does not explicitly name alternative sibling tools like run_feature_outcome_falsification_audit or run_feature_outcome_power_audit, so routing among similar research tools remains implicit.

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