Skip to main content
Glama

Exit check

exit_check

SEVEN CHAINS, FROM LIVE RESERVES OR AN AGGREGATOR QUOTE (for an executed sell test use arc_exit_check on Arc or base_exit_check on Base). Before you buy a token, find out whether you can sell it. Give a token address and a position size in USD and this returns what you would actually receive, the slippage, and the largest position that exits under 5%. WORKS ON SEVEN CHAINS: Solana and X1 (base58 address, constant-product maths against the pool's live reserves and its own fee) and five EVM chains (0x address, routed through LI.FI to USDC) - Base 8453 (the default), Ethereum 1, Arbitrum 42161, Optimism 10, Polygon 137. Any other chain id returns UNSUPPORTED_CHAIN and names these five; it is never reported as a token you cannot sell. This is deliberately NOT a safety grade. Safety grades describe the contract (mint authority, LP burn, holder count); exitability describes the depth. A token can score 100 on every safety check and still be untradeable — PROOF does exactly that in our own data. Verdicts on Solana/X1: EXITABLE, PARTIAL, COSTLY, TRAPPED, THIN, NO_POOL, UNPRICED. On EVM: EXITABLE, PARTIAL, COSTLY, THIN, NO_ROUTE, UNKNOWN. NO_ROUTE means the aggregator we check found no way out, which is strong evidence and not proof that no venue anywhere will take it; UNPRICED and UNKNOWN mean we could not resolve a value and are NOT judgements about the token. PAID: $0.004 per call over x402 (USDC on Arc, Base or Solana, or XNT on X1; no key, no sign-up) at https://apexfaucet.xyz/api/x402/exit-check/{mint}?usd=&chain=. Over MCP this tool answers with that price and URL, not the data.

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": {
      "mint": "<mint>"
    },
    "name": "exit_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
usdNoPosition size in USD you intend to exit. Optional — omit to get the largest clean exit instead.
mintYesToken address. A 0x address is an EVM token (Base unless you set `chain`); a base58 address is Solana or X1.
chainNoEVM chain id for a 0x address. Default 8453 (Base). Ignored for base58 addresses.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / chain
      Added value: +{
      +  "description": "EVM chain id for a 0x address. Default 8453 (Base). Ignored for base58 addresses.",
      +  "type": "number"
      +}
    • changedInput schema / properties / mint / description
      Previous value: -"Token mint address (base58)."New value: +"Token address. A 0x address is an EVM token (Base unless you set `chain`); a base58 address is Solana or X1."
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: it discloses the PAID model ($0.004/call over x402, USDC on Arc/Base/Solana or XNT on X1, no key), the exact endpoint, the per-chain verdict vocabularies, and the failure mode for unsupported chain ids (UNSUPPORTED_CHAIN naming the five, never misreported as unsellable). Importantly it warns that over MCP the call returns a price and URL rather than the data itself. The only gap is that it does not say what the response object contains or whether results are cached — minor for a paid quote tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is dense and mostly earns its place, but the opening is not front-loaded — it begins mid-thought with "SEVEN CHAINS, FROM LIVE RESERVES..." rather than stating what the tool does. The all-caps emphasis and the endpoint/payment-rail detail (URL template, XNT, faucet domain) are verbose for a tool description, though the payment model is genuinely necessary information.

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 three-parameter paid quote tool with no output schema, the definition covers the chain matrix, address formats, verdict enums per chain family, ambiguous-verdict caveats (NO_ROUTE, UNPRICED, UNKNOWN), the unsupported-chain error, and the fact that the MCP surface returns a price and URL rather than data. Nothing an agent needs to decide whether and how to call it 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning the schema lacks: the exact set of valid chain ids (8453, 1, 42161, 10, 137) versus the default, the base58-vs-0x address disambiguation, and the semantics of omitting `usd` (largest position that still exits under the 5% threshold). That goes beyond restating the property docs.

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 (give a token address and USD size, get back the proceeds, slippage, and the largest position that exits under 5%) and enumerates the seven supported chains with their address formats. It also explicitly distinguishes itself from arc_exit_check and base_exit_check, which are the executed-sell-test siblings, so an agent can route correctly without opening either schema.

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?

It names the decision the tool serves ("Before you buy a token, find out whether you can sell it"), names the alternatives for the executed-sell case, and draws a hard exclusion against safety-grade tools ("This is deliberately NOT a safety grade"). It even explains why the exclusion matters with a concrete counterexample of a token scoring 100 on safety yet being untradeable.

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