Skip to main content
Glama

open_live_quant_terminal

Launch the Lumina Live OrderBook & Quant Risk Web Terminal in a browser to visualize real-time L2 order books, volume imbalance rankings, and risk maps.

Instructions

Launch and open the interactive dark-mode Lumina Live OrderBook & Quant Risk Web Terminal in the user's browser (http://127.0.0.1:8765). [日本語検索キーワード: Lumina ライブ板 / 板画面 / オーダーブック画面 / リスク画面 / ターミナル / ランキング画面を開く]

Displays 3 real-time visual panels simultaneously:

  1. Multi-Asset OFI & Volume Imbalance Ranking Radar (clickable watchlist)

  2. Live auto-ticking 60-level L2 Order Book DOM Ladder + Cumulative Depth Chart (Crypto) or 24-bin Volume-at-Price POC/VAH/VAL Histogram (Stocks / Gold / FX)

  3. Closed-Bar Trend Stack, Intraday ADR15 Fuel Tank Gauge, and 1.5R / 3.0R Long & Short Blueprints. Call this tool whenever the user asks to visually see or open the order book, chart, ranking board, or Lumina terminal UI.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "open_live_quant_terminal"
  }
}

Input Schema

NameRequiredDescriptionDefault
symbolNoBTC-USD
timeframeNo1h
watchlistNoBTC-USD,ETH-USD,SOL-USD,NVDA,TSLA,XAUUSD

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose the side effect (opening the user's browser at a fixed localhost URL) and the fixed port. It is silent on prerequisites (is the server already running, or does this start it?), what happens on port conflict or failure, whether the call blocks, and whether it returns a URL or just confirmation. Useful but incomplete for a side-effecting launch tool.

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?

Front-loaded with the action and URL, then a clean numbered panel breakdown that earns its place by mapping to the user phrasings the tool must match ('order book', 'ranking', 'chart'). The Japanese keyword block is somewhat bulky but functions as a search-intent alias list; overall low waste.

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?

An output schema exists, so return values need not be described. However, for a launch tool with three undocumented parameters and no annotations, the description should at minimum cover the symbol/timeframe/watchlist meaning and the localhost-server prerequisite; those gaps leave the agent guessing when a call is valid.

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 0% for all three parameters (symbol, timeframe, watchlist), and the description never explains any of them — no accepted symbol format, timeframe enumeration, or watchlist delimiter semantics. The panel narrative hints that watchlist drives the multi-asset ranking and that a coin/stock/FX asset class changes panel 2's rendering, but that requires inference rather than being stated as parameter meaning.

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 states a specific verb+resource: launch/open an interactive web terminal at http://127.0.0.1:8765, and enumerates exactly what appears in it (ranking radar, L2 DOM ladder, trend stack). It implicitly separates itself from data-returning siblings like get_live_l2_orderbook by stressing 'visually see or open ... terminal UI', but never names an alternative, so it stops short of a 5.

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?

'Call this tool whenever the user asks to visually see or open the order book, chart, ranking board, or Lumina terminal UI' gives a concrete trigger condition tied to visual/UI intent. The word 'visually' is the discriminator against pure-data tools, but no exclusion or named alternative is stated explicitly.

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