Skip to main content
Glama

Veriql x402 seller check

veriql_x402_seller_check

Probes an x402 endpoint's 402 terms and screens requested payee wallets against OFAC, Drain Watch, Tether and Circle freezes before payment; returns GO, CAUTION or STOP.

Instructions

Before paying an x402 endpoint: reads its 402 (version, networks, testnet or not, the real price when the asset is USDC) and screens every wallet it asks to be paid at against OFAC, Drain Watch and Tether and Circle freezes. Answers GO, CAUTION or STOP. GO does not mean the seller delivers.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "veriql_x402_seller_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoThe x402 endpoint to probe (https)
payToNoA seller wallet to screen, with or without a url

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.1

TDQS

A4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does well on substance: it discloses what is read from the 402 (version, networks, testnet flag, real USDC price), which sanctions/freeze lists are screened (OFAC, Drain Watch, Tether, Circle), and the tri-state verdict. What it omits is operational behavior — whether the probe requires an API key, how long it takes, how failures or unreachable endpoints are reported, and whether payTo-only screening works without a url.

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?

Two tight sentences: the capability statement front-loads the trigger and the mechanism, then closes with the output vocabulary and a necessary caveat. No filler, and the caveat earns its place because it prevents over-trust in a GO verdict.

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?

For a two-param, no-output-schema probe, the definition covers inputs, the data inspected, and the return vocabulary well enough to call correctly. The remaining gap is failure/edge-case behavior (unreachable endpoint, non-x402 server, payTo-only invocation) which matters for a tool whose whole purpose is a pre-flight check.

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 description coverage is 100%, so both parameters are already documented (url as the endpoint to probe, payTo as a seller wallet 'with or without a url'). The description's phrase 'every wallet it asks to be paid at' hints that payTo addresses come from the 402 response rather than solely from the caller, but it never clarifies the optional/optional relationship or what happens when only one of the two is supplied.

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 resource ('reads its 402 ... and screens every wallet it asks to be paid at') plus the initial condition ('Before paying an x402 endpoint'). The three possible verdicts are named, so an agent knows exactly what this tool produces and can distinguish it from generic screening siblings like veriql_batch_screen or veriql_scan.

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?

The opening 'Before paying an x402 endpoint' gives a clear trigger condition, and the closing caveat ('GO does not mean the seller delivers') sets expectations about what the verdict does not guarantee. It does not name any alternative tool or say when to use veriql_preflight or veriql_batch_screen instead, so it stops short of explicit routing.

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