Let your shopping agent check the shop before it pays: a real, active, EU-registered company?
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between overlapping operations. Its purpose (verify a merchant behind a web shop before payment) is stated explicitly and narrowly.
check_merchant is a clean, predictable verb_noun snake_case name that accurately describes the action. With a single tool there are no competing conventions to conflict with it.
The server is intentionally single-purpose and the one tool is genuinely substantial rather than trivial, so the count is defensible. Still, a one-tool surface sits at the thin end of the range; a quota/status call or bulk variant would round it out.
The tool bundles the full verification pipeline — register lookup, VAT/VIES validation, sanctions screening, domain age, TLS and phishing checks — with layered match outcomes, which is strong coverage for the domain. Minor gaps remain: no way to query remaining lookup quota or verify multiple shops in one call.
Check a web shop BEFORE paying it: is the shop on this domain a real, active, registered company in a European business register, and does the domain belong to that company? Reads the registration / VAT number the shop states on its own imprint, terms or footer, looks it up in the national register (Denmark, Sweden, Norway, Finland, UK, Germany and other EU countries), validates VAT in VIES/HMRC, screens the company against sanctions lists, and checks domain age, TLS certificate and a public phishing list. Returns match = verified | partial | not_found | attention with evidence per signal and the source of each field. Evidence, not a verdict — you decide. Pass vat_number (and country) from the checkout or invoice when you have it; it also catches a checkout VAT number that belongs to a different or ceased company. When the free monthly lookups run out, the result contains buy_url: show it to your user — one payment adds 150 lookups.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | The shop's domain or URL, e.g. "example-shop.dk" | |
| country | No | ISO country code of that number, e.g. "dk", "se", "uk" — helps read a bare number | |
| vat_number | No | VAT or company registration number shown at checkout / on the invoice, e.g. "DK27528430" or "556710-4699" | |
| company_name | No | Company name shown at checkout, if any |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnly/idempotent/openWorld, but the description discloses the data sources consulted (national registers, VIES/HMRC, sanctions lists, TLS, phishing list), the result vocabulary, and a rate-limit/quota model with a paid unlock. That is substantial behavior beyond the structured fields.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Long but dense and front-loaded: the core question comes first, the signal list second, the return vocabulary and quota mechanics last. Every sentence carries information, though the enumeration of registers is slightly heavier than needed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description steps in to describe the return shape (match = verified | partial | not_found | attention with per-signal evidence and field sources) and the quota/buy_url flow. An agent has everything needed to call it and interpret the result.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning: it explains why vat_number matters (catching a number belonging to a different or ceased company) and that country disambiguates a bare number. company_name is not elaborated, keeping it short of a 5.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource with explicit scope: 'Check a web shop BEFORE paying it' and then spells out exactly what is checked (registration, VAT, sanctions, domain age, TLS, phishing list). There are no siblings to distinguish from, but the purpose is unambiguous and self-contained.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit timing ('BEFORE paying'), the condition for the optional vat_number parameter ('from the checkout or invoice when you have it'), and an operational instruction for quota exhaustion ('show buy_url to your user'). The when-to-use and how-to-react guidance is unusually complete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_merchantCheck a European business before you pay or sign.
EU compliance checks for AI agents: sanctions, company, VAT ID, IBAN, email. Pay per call.
Merchant verification for AI shopping agents.
Is a website ready for AI shopping agents? Readiness score (0-100) + agent shopping simulation.
Add one secure layer between your agents and this server.
