Skip to main content
Glama

Lancer un test d'achat privé

lancer_test

Starts a PRIVATE full purchase test of ANY online store by the Neoavis AI shopping agent: it looks for the product, opens its page, adds it to the cart and goes to checkout, without paying. Requires an Agency plan access key (X-Api-Key header, or ?cle=nk_… in the server URL); each test counts against the key's monthly quota. Use it when the user asks to test, audit or re-test a store (a client's site, a competitor, a check before launch). To read what Neoavis already published about a tracked store, use consulter_marchand (free); for an instant machine-readability check without a purchase journey, use verifier_site (free). Returns: id (test id), statut (en_attente), domaine, produit, dossier (private evidence report page to give the user), resultat (URL of the JSON result), delai (the test runs asynchronously, usually within the hour on business days) and quota (par_mois, utilises, restants, remise_a_zero). Then call lire_test with the id. Error results, never counted against the quota: no key or a key without tests (the answer gives the plan page), monthly quota reached (with the reset date), three tests already pending, invalid site or product. Nothing is published: a private test never changes a public Neoavis page.

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": "lancer_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteYesDomain or URL of the online store to test, e.g. exemple-boutique.fr.
langueNoLanguage of the evidence report page and of the notification e-mail: fr (default) or en.
produitNoProduct the agent will look for on the store, 2 to 60 characters, e.g. "crème hydratante". Optional only for a store Neoavis already tracks, where the usual test product is used.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say non-read-only, openWorld and non-idempotent; the description adds quota consumption per key, the Agency plan requirement and X-Api-Key/?cle= mechanism, the asynchronous delay (usually within the hour on business days), the explicit non-publication guarantee, and the four error classes that are not charged against quota. That is substantially more than the structured fields carry.

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?

Despite its length, each sentence carries load — scope, prerequisites, alternatives, return fields, error cases, publication guarantee. It is a single dense paragraph, though, and the returns/errors lists would be easier to scan if segmented.

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, and the description compensates by enumerating the returned fields (id, statut, domaine, produit, dossier, resultat, delai, quota sub-fields) and the async follow-up. For a quota-metered, open-world, asynchronous tool this covers everything an agent needs before calling.

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 coverage is 100%, so site, langue and produit are already documented, and the description repeats rather than extends their meaning. The only added semantics is that produit is optional for already-tracked stores via the 'usual test product' behaviour, which the schema also states.

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?

The description opens with a specific verb and resource — a full private purchase test of an online store, enumerating the agent's journey (search, open page, add to cart, checkout, no payment). It also explicitly distinguishes itself from the siblings consulter_marchand (read published data) and verifier_site (machine-readability without a purchase journey).

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?

It names concrete when-to-use triggers (test, audit, re-test a client's site, competitor, pre-launch check) and pairs each alternative with the condition that selects it: consulter_marchand is free read-only, verifier_site is free instant checking. It also points to the mandatory next step, lire_test with the returned id.

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