AgentFeed

Liquidation cascade alert

get_cascade_alert

Read-onlyIdempotent

Liquidation cascade detector for the 5 majors (SOL, BTC, ETH, XRP, DOGE): returns cascades active NOW - clustered same-side liquidations with symbol, side, USD total, prints, duration, severity (minor/major/extreme). Empty cascades array = no cascade in window. For every USDT perp we record across 3 exchanges, use get_cascade_scan. Costs 0.01 USDC per call (x402, USDC on Solana or Base).

Input Schema

TableJSON Schema

Name	Required	Description
`window`	No	lookback window seconds, 30-300, default 90
`min_usd`	No	min summed USD, default 50000
`min_events`	No	min prints to qualify, default 4

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes	the get_cascade_alert payload; a real captured example is free at https://x402.ochinimus.app/api/sample/get_cascade_alert
`tool`	Yes	the tool that produced this payload

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 25, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "additionalProperties": {},
+      "description": "the get_cascade_alert payload; a real captured example is free at https://x402.ochinimus.app/api/sample/get_cascade_alert",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "tool": {
+      "const": "get_cascade_alert",
+      "description": "the tool that produced this payload",
+      "type": "string"
+    }
+  },
+  "required": [
+    "tool",
+    "data"
+  ],
+  "type": "object"
+}

First observedSep 6, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already mark the tool read-only, idempotent, and non-destructive, and the description adds meaningful behavioral context: it costs 0.01 USDC per call payable via x402, is time-sensitive ('active NOW'), and returns a structured cascade summary with severity levels. This goes well beyond the structured metadata.

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?

Three sentences carry the full scope, output shape, empty-case behavior, sibling routing, and cost. It is front-loaded with what the tool does and contains no filler or redundant restatement of the schema.

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 read-only detector with three optional parameters, an output schema, and safe annotations, the description is complete: it covers the target symbols, the returned fields, the no-result case, the cost, and the correct alternative tool. Nothing essential is missing for an agent to invoke 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?

The input schema already documents all three parameters with descriptions and defaults, so schema coverage is 100%. The description does not need to restate parameter semantics, but it also does not add extra detail about how the parameters affect cascade detection beyond what the schema provides.

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-plus-resource purpose: it detects and returns currently active liquidation cascades for exactly five majors. It clearly distinguishes itself from get_cascade_scan by naming the broader perp universe as the alternative, so an agent can tell the tools apart without inspecting schemas.

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?

Usage context is explicit: this tool is for the 5 majors, and if the agent needs every USDT perp across 3 exchanges it should use get_cascade_scan. It also clarifies the empty-array meaning, so an agent knows how to interpret a no-cascade result.

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

All AgentFeed tools Inspect

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.