Liquid Agent

Website tech: what a local business site runs on (paid, $0.005)

leads_tech

Read-only

PAID over x402 inside this tool call ($0.005 USDC on Base or Arc per lookup that finds a verified site; no match, no charge): give a website or a US phone number and get the site platform (WordPress, Wix, Squarespace, Shopify...), online booking tool (Square Appointments, Vagaro, Calendly, Zocdoc...), payment system (Square, Toast, Clover, Stripe...), hiring and socials, read from the business's own verified website. Call once without payment to get the x402 PaymentRequired, then again with the signed payment in _meta["x402/payment"].

Input Schema

TableJSON Schema

Name	Required	Description	Default
`phone`	No	A US phone number, any format: 4043552001, (404) 355-2001, +14043552001. Give phone or domain.
`domain`	No	Or a website: example.com or https://www.example.com/contact.

Output Schema

TableJSON Schema

Name	Required	Description
`count`	No	Sites returned
`found`	No	Whether a verified site matched
`query`	No	The domain or phone looked up
`sites`	No	Each site: platform, online booking, payments, hiring, socials, copyright year
`checks`	No	How the data is read
`priceUsd`	No	Price of this call

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "checks": {
+      "description": "How the data is read",
+      "type": "string"
+    },
+    "count": {
+      "description": "Sites returned",
+      "type": "number"
+    },
+    "found": {
+      "description": "Whether a verified site matched",
+      "type": "boolean"
+    },
+    "priceUsd": {
+      "description": "Price of this call",
+      "type": "number"
+    },
+    "query": {
+      "additionalProperties": {},
+      "description": "The domain or phone looked up",
+      "properties": {},
+      "type": "object"
+    },
+    "sites": {
+      "description": "Each site: platform, online booking, payments, hiring, socials, copyright year",
+      "items": {},
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

AddedOct 12, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only cover the safety profile (readOnly, openWorld, non-idempotent, non-destructive). The description goes well beyond them: exact price and chain, the no-match-no-charge rule, the two-call x402 handshake with the _meta["x402/payment"] key, and the fact that data is read from the business's own verified site. Non-idempotency is implicitly surfaced by re-payment on each call.

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 the two facts an agent must know first (PAID, $0.005, per-lookup) and keeps the enumeration of returned fields compact. The opening parenthetical is dense and slightly overloaded, but no sentence is filler.

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?

An output schema exists so return-value shape need not be described, and annotations cover safety. For a paid, open-world lookup the description supplies everything an agent needs to attempt a correct call: inputs, price, free-probe-then-pay flow, and the source of truth for the data.

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% and both parameters already document accepted formats (phone variants, domain with scheme/path) plus the 'phone or domain' either/or rule. The description restates the same choice ('give a website or a US phone number') without adding constraints or precedence, so the 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 concrete verb+resource ('give a website or a US phone number and get the site platform... booking tool... payment system') and enumerates the actual data categories returned. It is clearly distinguishable from siblings like leads_lookup, leads_search, and leads_count, which do not return tech-stack signals.

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?

Gives strong operational context (paid per verified lookup, no match = no charge, one unpaid probe call then a paid retry with the x402 payment in _meta). What it lacks is an explicit statement of when to prefer this over leads_lookup/leads_search for the same business, so the routing among lead siblings is left implicit.

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

All Liquid Agent 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.