Skip to main content
Glama

APEX Faucet

by xyz.apexfaucet
OverviewDiscussionsAdmin

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.

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

A4.8/5.0
Behavior5/5

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

With no annotations the description carries the full burden and does so: it enumerates all verdict values per chain family, explains edge semantics (UNSUPPORTED_CHAIN is never reported as unsellable; NO_ROUTE is strong evidence, not proof; UNPRICED/UNKNOWN are non-judgements), and discloses the critical operational fact that over MCP this tool returns the price and x402 URL rather than the data, plus the $0.004 per-call cost.

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-loaded with purpose, then mechanics, verdicts, pricing and integration caveat in a logical order; nearly every sentence carries information an agent needs. It is nonetheless very long and repeats the chain enumeration (the 'seven chains' claim is followed by the full list again), which is mild redundancy rather than waste.

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 complex multi-chain, no-annotation, no-output-schema tool, the description covers supported chains, address-format branching, default chain, error states, verdict taxonomies, cost, and the MCP-specific response limitation. Nothing an agent needs to call it correctly or interpret it seems 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 and the schema already documents mint, usd and chain. The description adds value beyond it by mapping raw chain ids to named networks (8453 Base default, 1 Ethereum, 42161 Arbitrum, 10 Optimism, 137 Polygon), which the schema does not spell out.

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 and outcome ('find out whether you can sell it', returns what you'd receive plus slippage and max position under 5%), and explicitly distinguishes itself from sibling exit tools (arc_exit_check, base_exit_check) and from safety-grade tools. An agent can identify resource and scope without opening the 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?

Gives an explicit when ('before you buy a token'), names the alternative for an executed sell test (arc_exit_check / base_exit_check), and explicitly says what this is NOT ('deliberately NOT a safety grade'), with the reasoning that safety and exitability measure different things. No inference required.

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

All APEX Faucet toolsInspect
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.

Resources