Skip to main content
Glama

Recent liquidations

recent_liquidations
Read-only

Recent forced liquidations of one asset's USDT perpetual on OKX (the only venue reachable from the US that publishes a liquidation feed): long vs short liquidated count, size and USD value over the last 0.25–24 hours, the largest ones, an hourly breakdown, and where they cleared relative to the current mark price in adjustable % bands. These are realized liquidations, not estimated liquidation levels. Reports how much of the window the feed covered. Fails (and is not charged) if OKX doesn't answer or lists no such perpetual. Costs $0.003 USDC per call.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "symbol": "<symbol>"
    },
    "name": "recent_liquidations"
  }
}

Input Schema

NameRequiredDescriptionDefault
hoursNoLook-back window in hours, 0.25–24 (default 4)
symbolYesBase asset or pair, e.g. 'BTC', 'ETH', 'SOLUSDT'
bucketPctNoWidth of the price bands around the mark price, in %, 0.1–5 (default 0.5)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

With annotations only covering readOnly/openWorld, the description adds substantial behavioral detail: realized vs estimated data, feed-coverage reporting on the window, hard failure with no charge, and explicit pricing at $0.003 USDC per call. These are exactly the operational facts an agent needs before calling.

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?

The output inventory, the realized-vs-estimated caveat, coverage disclosure and pricing are all useful and front-loaded. It runs as one long sentence chain, which is dense, but no sentence is 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?

No output schema exists, yet the description effectively enumerates the return payload (breakdowns, largest liquidations, band distribution) plus coverage metadata and the failure mode. For a 3-parameter read-only tool, nothing an agent needs is missing.

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 hours, symbol and bucketPct are already documented, including defaults and ranges. The description restates the band concept ('where they cleared relative to the current mark price in adjustable % bands') and the time window but adds no syntax or format detail beyond the schema.

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?

States a specific verb+resource ('recent forced liquidations of one asset's USDT perpetual on OKX') and enumerates the outputs (long/short counts, size, USD value, largest, hourly breakdown, mark-price bands). It also explicitly distinguishes itself from the estimated-levels sibling: 'These are realized liquidations, not estimated liquidation levels.'

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 on applicability: OKX-only venue, USDT perpetuals, window 0.25–24h, and the failure condition when the venue doesn't answer or lists no such perpetual. It does not name the sibling tool (e.g. liquidation_risk) it should be preferred over, leaving that routing to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources