Skip to main content
Glama
tedorigawa001

TradingView-MCP

run_external_label_study

Measures forward outcomes for external point-in-time labels on the active chart, testing series like daily open interest with the same outcome, fold, and interval machinery as built-in conditions.

Instructions

Measure forward outcomes for caller-supplied point-in-time labels on the active chart, so an external series such as daily open interest, settlement statistics or survey data can be tested with the same outcome, fold, interval and journal machinery as the built-in conditions. Each label is attached to a bar at least one bar after the one it carries, because an external label is rarely public when its own bar closes; a zero lag is refused rather than trusted. Horizons count subsequent observed bars, so a daily series is not voided by weekends. Unlike run_market_event_study this accepts daily and weekly timeframes. Label correctness and revisions belong to whoever supplied them; only the join is point-in-time here. Signal-bar close is an event reference, not an assumed fill. It never ranks labels, changes the chart, or places orders.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoMost recent loaded bars to inspect. Default: 1000
foldsNo
journalNo
horizonsYes
event_limitNoMaximum per-event rows to return. Aggregate metrics always use all events. Default: 50
observationsYesPoint-in-time labels. time must identify a loaded bar, exactly or by a UTC date only one bar carries
minimum_eventsYes
overlap_policyNoExclude later events whose window overlaps an earlier one, or keep them for a dense daily label series and accept intervals narrower than the effective sample. Default: exclude_later_event
accepted_labelsYesLabels to evaluate and the direction each one implies. Other labels are counted and dropped
expected_symbolYes
confidence_levelNo
target_return_bpsYes
expected_timeframeYes
configuration_trialsNo
observation_lag_barsYesClosed bars between the observation bar and the signal bar. Minimum 1

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.6/5.0
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 disclosure burden, and it does so exceptionally. It reveals that zero lag is refused, horizons count subsequent observed bars so weekends do not void daily series, label correctness belongs to the caller, signal-bar close is not an assumed fill, and the tool never ranks labels, changes the chart, or places orders.

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?

The description is lengthy but every sentence carries specific operational information. The core purpose is front-loaded, and the subsequent caveats about lag, horizons, timeframes, and side effects are all necessary for correct invocation. There is no filler or redundancy.

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

Completeness4/5

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

For a 15-parameter tool with no annotations and no output schema, the description provides strong contextual grounding around the data join, lag behavior, timeframe support, and non-effects. It is not fully complete because it never describes the return shape or how fold/journal/confidence configurations interact, and some required quantitative parameters are left to inference. Still, it is far above the minimum viable definition.

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

Parameters3/5

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

Schema description coverage is only 40%, so the description must compensate. It does add real meaning for the central concepts: observation lag, horizons, labels, and accepted label directions. However, required parameters such as target_return_bps, minimum_events, folds, and journal settings receive little or no descriptive help, and expected_symbol/expected_timeframe matching against the active chart is implied rather than stated.

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 'Measure forward outcomes for caller-supplied point-in-time labels on the active chart', giving a specific verb, resource, and input type. It also explicitly distinguishes itself from run_market_event_study by noting daily/weekly timeframe support, so an agent can tell which tool is appropriate.

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?

It clearly states the intended use case: testing external series such as open interest, settlement statistics, or survey data with the same machinery as built-in conditions. It directly names the main alternative, run_market_event_study, and explains the differentiator that this tool accepts daily and weekly timeframes, effectively providing when-to-use and when-not-to-use guidance.

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