AgentFeed

Collateral exit liquidity

get_exit_quote

Read-onlyIdempotent

EXIT LIQUIDITY on seized collateral: what a liquidator ACTUALLY realises selling a Kamino reserve into live routing, versus the oracle price the protocol marks it at. Returns max_exitable_usd (largest clip whose liquidator margin is still positive, found by bisection, with its resolution width), the exitable fraction, the conservative bound at the 2% penalty floor, and for the nearest clip actually probed: realised USD, haircut bps and liquidator margin bps. Distinguishes a router that REFUSES to quote a token (permissioning, not illiquidity) from a book with no route (a real liquidity finding) - they are different facts and were one status until this split. A terminal verdict requires six consecutive agreeing observations from the symbol's own tape, so a single bad quote cannot produce a finding; withheld verdicts fall back to the last corroborated measurement with its age rather than returning null. Zero bad debt today does not disprove any of this - it means nobody has been forced to test it at size. Method, corroboration rules and row counts are free via get_exit_method. Costs 0.02 USDC per call (x402, USDC on Solana, Base, Polygon, Arbitrum or Arc).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`symbol`	Yes	reserve symbol e.g. SPYx, cbBTC, FWDI, CRCLx (get_exit_method lists all covered)
`size_usd`	No	clip size in USD you would need to exit; the nearest MEASURED clip is returned, never interpolated

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes	the get_exit_quote payload; a real captured example is free at https://x402.ochinimus.app/api/sample/get_exit_quote
`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_exit_quote payload; a real captured example is free at https://x402.ochinimus.app/api/sample/get_exit_quote",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "tool": {
+      "const": "get_exit_quote",
+      "description": "the tool that produced this payload",
+      "type": "string"
+    }
+  },
+  "required": [
+    "tool",
+    "data"
+  ],
+  "type": "object"
+}

First observedSep 6, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations only declare safety (readOnly, idempotent), so the description adds real behavioral context: REFUSED-quote vs no-route status distinction, six consecutive agreeing observations required before a verdict, fallback to last corroborated measurement with its age rather than null, and the caveat that zero bad debt doesn't disprove findings. This is exactly the kind of non-obvious behavior an agent needs.

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-loads purpose, then lays out return fields and the corroboration/refusal nuances. The sentences are dense and mostly earn their place, but the parentheticals and the 'zero bad debt' caveat push toward long-windedness.

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

Completeness4/5

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

An output schema exists, so return-value explanation isn't required, yet the description still names key fields (max_exitable_usd, exitable fraction, conservative bound, nearest-probe realised USD/haircut/margin). With annotations covering safety and the schema covering both params, only minor gaps remain (e.g., exact cost flow timing for x402).

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% and both parameters already carry their meaning (symbol examples; size_usd maps to nearest MEASURED clip, never interpolated). The description reinforces the 'nearest clip actually probed' idea but adds no syntax or format detail beyond the schema. Baseline 3 applies.

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 (measure exit liquidity on seized collateral) against a specific resource (a Kamino reserve sold into live routing, versus oracle price), and enumerates its return fields. Distinguishable from siblings in a crowded liquidation family, and explicitly points to get_exit_method for the method.

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?

Sets clear context (measuring realisable exit value on seized collateral) and points to get_exit_method for method/corroboration details, plus discloses the 0.02 USDC x402 payment. It doesn't name a sibling that should be used instead when you don't need liquidity measurement, but the intended use case is unambiguous.

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.