Skip to main content
Glama

Market-wide liquidations

market_liquidations
Read-onlyIdempotent

The whole market's forced closes in one call rather than per pair: 24h dollars and counts split long vs short, hour by hour so a cascade is locatable, ranked by coin, plus the biggest single event. Perp dollars come from the venues that publish a liquidation feed, not from every venue we stream, and the Hyperliquid share is a sample of that venue read from tracked wallets, so the totals are a FLOOR. Includes named_liquidations, the wallets that were closed out on Hyperliquid, which no other venue publishes. lending_liquidations rides alongside as a SEPARATE lane (an on-chain debt repaid and collateral seized) and must never be added to the perp numbers. A long is force-closed by selling, so long dollars are sell-side pressure. Descriptive market data only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoOne line saying what the numbers cover, or why there are none. Read it before reporting any zero as a market reading.
as_ofNoWhen the combined snapshot was taken, as an ISO stamp.
staleNoTrue when the snapshot is older than it should be.
coverageNoWhich feeds fed this snapshot.
availableNoFalse when this lane could not answer: a producer is dark, the pair sits outside this plan, or the argument named something we do not carry. Absent or true means the numbers are a real reading, not a guess.
perp_liquidationsNoThe 24h forced-close picture on leveraged markets: count, total_usd, the long and short split in both dollars and counts, hour by hour, the peak hour, the ranked coins, the biggest single event, and which exchanges are behind the totals. Long dollars are sell-side pressure. held_out names anything removed before these numbers were built (how many rows, how many dollars, on which symbols and why), or is null when nothing was; those dollars are NOT inside any figure here.
named_liquidationsNoHyperliquid closures with the wallet named, which no other market publishes.
lending_liquidationsNoA SEPARATE 24h lane: on-chain debts repaid and collateral seized. count, total_usd, protocols, chains and recent rows. Never add these to the leveraged numbers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / perp_liquidations / description
      Previous value: -"The 24h forced-close picture on leveraged markets: count, total_usd, the long and short split in both dollars and counts, hour by hour, the peak hour, the ranked coins, the biggest single event, and which exchanges are behind the totals. Long dollars are sell-side pressure."New value: +"The 24h forced-close picture on leveraged markets: count, total_usd, the long and short split in both dollars and counts, hour by hour, the peak hour, the ranked coins, the biggest single event, and which exchanges are behind the totals. Long dollars are sell-side pressure. held_out names anything removed before these numbers were built (how many rows, how many dollars, on which symbols and why), or is null when nothing was; those dollars are NOT inside any figure here."
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "properties": {
      +    "as_of": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "When the combined snapshot was taken, as an ISO stamp."
      +    },
      +    "available": {
      +      "anyOf": [
      +        {
      +          "type": "boolean"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "False when this lane could not answer: a producer is dark, the pair sits outside this plan, or the argument named something we do not carry. Absent or true means the numbers are a real reading, not a guess."
      +    },
      +    "coverage": {
      +      "description": "Which feeds fed this snapshot."
      +    },
      +    "lending_liquidations": {
      +      "anyOf": [
      +        {
      +          "additionalProperties": {},
      +          "propertyNames": {
      +            "type": "string"
      +          },
      +          "type": "object"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "A SEPARATE 24h lane: on-chain debts repaid and collateral seized. count, total_usd, protocols, chains and recent rows. Never add these to the leveraged numbers."
      +    },
      +    "named_liquidations": {
      +      "anyOf": [
      +        {
      +          "items": {},
      +          "type": "array"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Hyperliquid closures with the wallet named, which no other market publishes."
      +    },
      +    "note": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "One line saying what the numbers cover, or why there are none. Read it before reporting any zero as a market reading."
      +    },
      +    "perp_liquidations": {
      +      "anyOf": [
      +        {
      +          "additionalProperties": {},
      +          "propertyNames": {
      +            "type": "string"
      +          },
      +          "type": "object"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "The 24h forced-close picture on leveraged markets: count, total_usd, the long and short split in both dollars and counts, hour by hour, the peak hour, the ranked coins, the biggest single event, and which exchanges are behind the totals. Long dollars are sell-side pressure."
      +    },
      +    "stale": {
      +      "anyOf": [
      +        {
      +          "type": "boolean"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "True when the snapshot is older than it should be."
      +    }
      +  },
      +  "type": "object"
      +}
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already mark it as read-only and idempotent. The description adds valuable behavioral context: totals are a floor (not exact), the Hyperliquid share is a sampled read from tracked wallets, and long dollars represent sell-side pressure. These go beyond the safety hints and inform interpretation of results.

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 description is dense but every sentence carries necessary information. It leads with the core purpose, then layers in limitations and interpretation. Slightly longer than minimal, but justified given the nuance required to prevent misuse.

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 tool with no parameters and an output schema available, the description covers all essential context: scope, data sources, limitations, separate lanes, and interpretational guidance. Nothing an agent needs to invoke it correctly is missing.

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

Parameters4/5

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

The tool has zero parameters, so the baseline is 4. The description adds substantial context about the output structure (hourly split, ranking, named_liquidations, lending lane) which helps the agent understand what the tool returns, though it does not need to explain parameter syntax.

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 explicitly states the tool retrieves market-wide forced closes, contrasting with per-pair calls. It names specific resources (whole market, perp dollars, Hyperliquid sample) and distinguishes it from sibling tools like coin_liquidations by scope.

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?

Provides clear guidance: use for a market-wide view rather than per pair, and explicitly warns that lending_liquidations is a separate lane that must never be added to perp numbers. This gives both when-to-use and when-not-to-mix instructions.

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