Skip to main content
Glama

Lumi Trades: x402 seller checks and test-buys

by io.github.cypher-osiris
OverviewDiscussionsAdmin

Lumi: x402 vendor observations (free)

lumi_vendor_scores
Read-only

Free. Check an x402 seller before you pay it: pass url (the resource you are about to buy), domain, or payTo (the address in its 402 quote, case-insensitive). Lumi ingests the full CDP x402 Bazaar catalog daily and runs free, unpaid 402-quote checks of listings on a rotating schedule (valid quote, price and payTo vs the listing, latency, domain age; live coverage counts in the response), labelled 'quote-checked, low confidence', plus Lumi's own test-buys confirmed on-chain, labelled 'test-bought' and counted per chain (Base USDC buys of Bazaar listings; XRPL buys of a small curated list, separately). Answer-only: the full coded verdict is in the free lumi_trust_check. Observations, not ratings; no match is not a negative finding. With no arguments: the curated XRPL vendor scores and catalog counts; vendor_id gives one curated vendor's summary (tx evidence is in the paid vendor report).

Input Schema

NameRequiredDescriptionDefault
urlNoResource URL you are about to pay, e.g. https://example.com/api/data
payToNopayTo address from the seller's 402 quote (0x... or r...)
domainNoSeller host or domain, e.g. example.com
vendor_idNoOptional curated vendor id, e.g. printmoneylab

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / vendor_id / description
      Previous value: -"Optional curated vendor id, e.g. asksurf"New value: +"Optional curated vendor id, e.g. printmoneylab"
  2. Changed4 schema fields changed
    • addedInput schema / properties / domain
      Added value: +{
+  "description": "Seller host or domain, e.g. example.com",
+  "maxLength": 253,
+  "type": "string"
+}
    • addedInput schema / properties / payTo
      Added value: +{
+  "description": "payTo address from the seller's 402 quote (0x... or r...)",
+  "maxLength": 120,
+  "type": "string"
+}
    • addedInput schema / properties / url
      Added value: +{
+  "description": "Resource URL you are about to pay, e.g. https://example.com/api/data",
+  "maxLength": 500,
+  "type": "string"
+}
    • changedInput schema / properties / vendor_id / description
      Previous value: -"Optional vendor id from the list, e.g. asksurf"New value: +"Optional curated vendor id, e.g. asksurf"
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond readOnlyHint/openWorldHint: it discloses data provenance (daily CDP x402 Bazaar ingest, rotating unpaid quote checks, separate on-chain test-buys per chain), the confidence labelling scheme ('quote-checked, low confidence' vs 'test-bought'), and the critical interpretive caveat that observations are not ratings and no match is not a negative finding.

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?

The 'Free.' + action sentence is well front-loaded and nearly every clause carries information an agent needs (labels, provenance, alternatives). The middle sentence is an overloaded run-on with stacked parentheticals, which makes it harder to scan than it needs to be.

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 zero-required-parameter, four-field read tool with no output schema, the description covers inputs, default behavior, data freshness, confidence interpretation, and where deeper answers live. Nothing an agent needs in order to call it correctly 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 already 100%, so the baseline is 3; the description adds real value by noting payTo matching is case-insensitive and by explaining what empty arguments return and what vendor_id yields. It stops short of describing precedence or behavior when multiple of url/domain/payTo are supplied together.

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 up front: 'Check an x402 seller before you pay it', with the three accepted lookups (url, domain, payTo) named immediately. It also differentiates itself from siblings by pointing to the free lumi_trust_check for the coded verdict and the paid vendor report for tx evidence.

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?

Explicitly frames the decision context ('before you pay it'), enumerates the alternative inputs, describes the no-argument default (curated XRPL vendor scores and catalog counts) and the vendor_id single-vendor path. It routes the agent to alternatives for anything deeper, so when-to-use and when-not-to-use are both covered.

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

All Lumi Trades: x402 seller checks and test-buys 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