Skip to main content
Glama
FerroxLabs

TVControl

by FerroxLabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

draw_shape

Draw lines, rectangles, text, and other shapes on TradingView charts with style overrides. Unknown shape names are refused to prevent accidental flags.

Instructions

Draw a shape/line on the chart. The created shape name is read back and an unrecognised name is REFUSED rather than silently becoming a flag.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textNoText content for text shapes
pointYes{ time: unix_timestamp, price: number }
shapeYesShape type. Verified on Desktop 3.3.0: horizontal_line, vertical_line, horizontal_ray, ray, cross_line, trend_line, rectangle, text, note, callout, balloon, price_label, arrow_up, arrow_down, flag, long_position, short_position, fib_retracement, anchored_vwap, fixed_range_volume_profile. An unknown name is refused, not silently drawn as a flag. For long_position/short_position, overrides takes stopLevel and profitLevel IN TICKS plus riskDisplayMode and alwaysShowStats, and TradingView computes the R:R itself.
point2NoSecond point for two-point shapes (trend_line, rectangle)
overridesNoJSON string of style overrides (e.g., '{"linecolor": "#ff0000", "linewidth": 2}')

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.5.3
    • changedInput schema / properties / shape / description
      Previous value: -"Shape type: horizontal_line, vertical_line, trend_line, rectangle, text"New value: +"Shape type. Verified on Desktop 3.3.0: horizontal_line, vertical_line, horizontal_ray, ray, cross_line, trend_line, rectangle, text, note, callout, balloon, price_label, arrow_up, arrow_down, flag, long_position, short_position, fib_retracement, anchored_vwap, fixed_range_volume_profile. An unknown name is refused, not silently drawn as a flag. For long_position/short_position, overrides takes stopLevel and profitLevel IN TICKS plus riskDisplayMode and alwaysShowStats, and TradingView computes the R:R itself."
  2. First observedv2.2.1

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals an important non-obvious trait: the created shape name is read back and unrecognized names are refused instead of silently becoming a flag. This goes beyond the schema by clarifying failure behavior. It doesn't discuss persistence or side effects, but for a drawing tool the core mutation is evident.

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 sentences, zero filler. The primary purpose is front-loaded, and the second sentence adds a high-value behavioral warning in compact form.

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 5-parameter tool with nested objects and no output schema, the description plus a fully covered schema is mostly complete. The read-back/refusal note supplies important edge-case behavior. Minor gaps remain around return value structure and where drawn shapes appear, but these don't block correct invocation.

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?

The top-level description carries no parameter details; the input schema already documents all five parameters with 100% coverage. Per the baseline, that is adequate but not enhanced. The refusal behavior is relevant to the shape parameter but duplicates what the schema's shape description already states.

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 specific verb and resource — 'Draw a shape/line on the chart' — which clearly identifies the action. It also distinguishes the tool from sibling tools by focusing on creation, while siblings like draw_list, draw_clear, and draw_remove_one cover listing, clearing, and removing shapes. No ambiguity about what this tool does.

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 opening sentence gives clear context: use this tool when you want to draw a shape or line on the chart. It does not explicitly name alternatives or state when not to use it, but among the draw_* siblings the creation-versus-management distinction is apparent enough for an agent to select correctly.

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

Deploy Server

Other Tools