Skip to main content
Glama

racket_check

Read-onlyIdempotent

Full Racket Check of a local service provider's website URL. Fetches the homepage plus the pricing, services, plans and terms pages it links to (same host, capped) and scores racket signals: subscription / plan / membership language, minimum-visit or package requirements, contract lock-in language (term agreements, termination fees, auto-renew), and pricing transparency — exact prices published vs call-for-quote only. Returns machine-readable JSON LED BY THE VERDICT — CLEAN / PLAN_PUSH / RACKET / UNKNOWN — plus a plain-language verdict line and a 0-100 score (100 = cleanest one-time provider), per-signal found/severity with evidence snippets from the site's own pages, the pages checked, and a pricing block (exact prices found, samples, call-for-quote-only flag). FAIL-CLOSED: if the site cannot be fetched or no readable service content comes back, the verdict is UNKNOWN with score null — never CLEAN on missing data. HONEST LIMITS: reads the public website only; it cannot see quotes given by phone or in person, and a site that hides its plan terms behind a login will read thinner than it is. Cost: $1.00 USDC on Base per call, paid via x402 — the caller's agent pays from its owner's approved wallet; no API key needed. Use this before booking any local service provider — lawn, cleaning, HVAC, pest control, and similar — to catch a subscription or minimum-visit push before it starts.

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": {
      "url": "<url>"
    },
    "name": "racket_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesService provider website URL to check for racket signals, e.g. https://example-lawncare.com

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only cover safety traits (readOnly, openWorld, idempotent, non-destructive), and the description goes well beyond them: it discloses the fail-closed UNKNOWN-on-empty behavior, the honest limits (phone/in-person quotes invisible, login-gated terms read thinner), and the exact cost/payment path ($1.00 USDC on Base via x402, no API key). The crawl scope (same host, capped) is also stated, which is behavior an agent cannot get from annotations.

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?

Every sentence carries real information: what is fetched, what is scored, the return shape, the failure mode, the limits, and the price. The weakness is ordering — the when-to-use guidance, arguably the most decision-relevant line, is buried at the very end, and the dense single-paragraph block makes the verdict/limits/cost sections hard to scan.

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 single-parameter tool with no output schema, the description supplies everything an agent needs: the returned JSON structure (verdict enum, verdict line, 0-100 score, per-signal severity with evidence snippets, pages checked, pricing block), the failure mode, the cost and payment mechanism, and the reliability caveats. Little an agent would need before calling is missing.

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?

With a single parameter at 100% schema description coverage, the schema already explains the URL field and gives an example, so the baseline is 3. The description adds only marginal meaning beyond it — that the URL is a local service provider's site and that crawling stays on the same host and is capped — without specifying input validation or URL edge cases.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource — a 'Full Racket Check' of a provider's website URL — and enumerates exactly what it fetches and scores (pricing, plans, services, terms pages; subscription language, minimum-visit requirements, contract lock-in, price transparency). The modifier 'Full' hints at a difference from the sibling racket_check_lite, but the description never states that distinction explicitly, so an agent must infer it from the name alone.

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?

Usage context is explicit and concrete: 'Use this before booking any local service provider — lawn, cleaning, HVAC, pest control, and similar — to catch a subscription or minimum-visit push before it starts.' That gives a clear trigger condition. It stops short of naming when NOT to use it or routing to the sibling racket_check_lite for a cheaper/shallower check, which is the one obvious gap given a $1.00 per-call cost.

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.