Skip to main content
Glama
Sign In

mcp

by com.bykaranteli
OverviewDiscussionsAdmin

Largest single liquidations and a 30-day session heatmap (counted venue feeds)

get_liquidation_leaderboard
Read-only

Call this when the user asks for the biggest liquidation today or this week, who got liquidated for the most, the largest single liquidation print, or when in the day or week liquidations cluster (Asia, Europe or US hours, weekday by UTC hour). Returns the largest single liquidation prints of the last 24h, 7d or 30d (rank, symbol, venue, side where SELL means a long was liquidated, price, quantity, notional, millisecond time) recorded from the counted venues' public feeds, plus a 30-day weekday by UTC hour heatmap with hour, weekday and session totals. A floor by construction: each venue's feed carries what the venue publishes (Binance at most one print per second per symbol); the counted venue list and each feed's status come from get_coverage.

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": "get_liquidation_leaderboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoDays folded into the session heatmap (default 30).
limitNoRows to return (default 25, max 100).
windowNoRanking window: 24h (default), 7d or 30d.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses the data source (counted venues' public feeds), a structural coverage limitation (venue-published prints, with Binance at most one per second per symbol), and where venue status comes from via get_coverage. It also explains the output fields and the SELL-side convention, which is useful behavioral context.

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 front-loaded with usage triggers, followed by return contents and then a concise data-quality caveat. Despite being dense, every sentence carries useful information and there is no filler.

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

Completeness5/5

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

For a complex, no-output-schema tool, the description explains what is returned, the ranking windows, the heatmap axes, and the main data limitation. It also points to get_coverage for venue-list and feed-status context, leaving little an agent needs in order to call it correctly.

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 coverage is 100%, so the input schema already documents days, limit, and window. The description restates the window choices and describes the heatmap, but it does not add meaning for days or limit and calls the heatmap '30-day' even though the days parameter is configurable from 7 to 90.

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 and resource: return the largest single liquidation prints over a chosen window plus a weekday-by-hour heatmap. The phrase 'largest single liquidation print' distinguishes it from broader liquidation-list or cascade tools without relying on the tool name alone.

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?

It gives clear trigger conditions: biggest liquidation today or this week, who was liquidated for the most, largest single print, or intraday/weekly clustering. It does not explicitly say when to avoid this tool or name the liquidation-list/cascade alternatives, so it stops short of full when-not guidance.

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

All mcp toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources