Skip to main content
Glama

Vérifier un site en direct

verifier_site
Read-onlyIdempotent

Live check of ANY online store, tracked by Neoavis or not: can an AI shopping agent read it without clicking? Reads the UCP checkout profile (/.well-known/ucp), structured product data, robots.txt access for shopping agents, llms.txt and sitemap, in a few seconds. Use it when the user wants to buy from a store that consulter_marchand does not know, or wants to know if their own store is ready for AI agents. For a store Neoavis already tested, consulter_marchand gives the full purchase test. Returns: points (out of 15), verdict (pret, partiel or pas_pret), criteres_reussis, neoavis (score out of 100 and page when tracked), resume (one sentence to quote), detail_gratuit_humain (page with the per-criterion detail for a human) suites_payantes (x402 URLs, USDC on Base, no account: per-criterion live check, and a full purchase test) and test_prive_agence (the Agency plan: the full purchase journey tested with lancer_test, delivered as an evidence report). Free: 10 checks per hour per address. Unreadable domain or unreachable site: error result.

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": {
      "site": "<site>"
    },
    "name": "verifier_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteYesDomain or URL of any online store, for example exemple-boutique.fr.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description stays consistent while adding what they cannot: latency (a few seconds), a concrete rate limit (10 checks per hour per address), and the failure mode (unreadable domain or unreachable site returns an error result). It also discloses the paid surfaces (x402/USDC on Base without an account) and an agency tier. The only thing left implicit is how long cached results remain valid between checks.

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 correctly: purpose, mechanism, then usage, then returns and limits. It is dense and runs long, and the return-key enumeration (criteres_reussis, detail_gratuit_humain, suites_payantes, test_prive_agence) is heavy, but that enumeration earns its place because there is no output schema. Minor waste in listing both score scales informally.

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?

No output schema exists, so the description carries the return contract itself and does: points out of 15, one of three verdicts, a quotable one-sentence resume, and named upsell URLs. It also covers error behavior, cost/quota bounds, and the sibling that handles the already-tracked case. Nothing an agent needs 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?

There is a single required parameter at 100% schema coverage, where the schema already says 'Domain or URL of any online store' with an example. The description's useful addition is that the store need not be tracked by Neoavis, which widens the accepted input beyond what the schema states. Otherwise it adds no format or normalization detail (e.g. whether a bare domain without scheme is required).

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?

Opens with a specific verb and resource: a live check of ANY online store, tracked or not, answering whether an AI shopping agent can read it without clicking. It then enumerates exactly what is read (UCP profile at /.well-known/ucp, structured product data, robots.txt, llms.txt, sitemap) and explicitly contrasts itself with consulter_marchand, so an agent can route 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 two concrete trigger conditions: the user wants to buy from a store consulter_marchand does not know, or wants to know if their own store is AI-agent ready. It also names the alternative and its different outcome (consulter_marchand = full purchase test for an already-tested store; lancer_test = Agency-plan journey test), which is exactly the when/when-not/alternative structure.

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.

Resources