Skip to main content
Glama

Izifete — prestataires événementiels en France

Demander un devis à un prestataire

creer_demande

Connexion à un compte Izifete requise ; l'email vérifié du compte est utilisé. Utilise cet outil UNIQUEMENT après que l'utilisateur a explicitement choisi un prestataire (via search/fetch) ET confirmé vouloir lui envoyer une demande de devis gratuite. Crée une demande ciblée (type d'événement, ville, date, budget indicatif, message) qui est relue par l'équipe Izifete avant transmission au prestataire. Demande toujours confirmation à l'utilisateur avant d'appeler cet outil. Aucune donnée de paiement n'est collectée. N'utilise pas cet outil pour rechercher (search), afficher une fiche (fetch) ou vérifier une entreprise (verifier_entreprise).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cityYesVille de l'événement
budgetNoBudget indicatif (optionnel, ex. « 1500 € »)
guestsYesNombre d'invités estimé
messageNoPrécisions de l'utilisateur pour le prestataire (optionnel)
event_dateYesDate de l'événement (ex. « 2026-09-14 » ou « 14 septembre 2026 »)
event_typeYesType d'événement : mariage, anniversaire, séminaire, baptême, soirée…
client_nameYesNom (ou prénom) de l'utilisateur qui fait la demande
postal_codeNoCode postal (optionnel)
provider_idYesIdentifiant du prestataire choisi (renvoyé par search/fetch)
client_emailNoRenseigné automatiquement depuis le compte OAuth vérifié. Ne demande jamais cette adresse à l'utilisateur.
client_phoneNoTéléphone de l'utilisateur (optionnel)

TDQS

A4.5/5.0
Behavior5/5

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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description discloses account/login requirements, the verification email usage, that the request is reviewed by the Izifete team before transmission, and that no payment data is collected. This adds valuable behavioral context not present in 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?

The description is moderately long but well-structured and front-loaded with the critical prerequisite. Each sentence serves a purpose (prerequisite, action, review process, confirmation, exclusions). Minor redundancy exists, but it remains concise for the complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers prerequisites, creation workflow, review process, exclusions, and account requirements. It does not explicitly state what the function returns after a successful call, but the absence of an output schema and the described handoff to Izifete provide sufficient context for most scenarios.

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% with every parameter described. The description mentions some fields (event type, city, date, budget, message) in passing but adds no further parameter-level meaning beyond the schema. Baseline 3 is appropriate.

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 clearly states the tool creates a targeted quote request ('Crée une demande ciblée') and distinguishes it from sibling tools by explicitly excluding search, fetch, and verifier_entreprise. The verb+resource combination is specific and unambiguous.

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?

The description provides explicit usage conditions: use only after the user has selected a provider and confirmed, always ask for confirmation before calling, and lists what the tool is NOT for (search, fetch, verifier_entreprise). This is exemplary guidance.

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.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool targets a distinct task: searching for providers, fetching details, creating a request, verifying a business, and two clearly separated advice channels (event organizer vs professional). The descriptions explicitly cross-reference to eliminate overlap, making misselection highly unlikely.

Naming Consistency3/5

Names mix French (conseils_evenement, creer_demande) and English (search, fetch) and follow different patterns: noun-based for advice, verb+noun for actions, and simple verbs. While readable and consistently lowercase with underscores, the lack of a single convention reduces predictability.

Tool Count5/5

Six tools is well-scoped for a directory and advice service, covering all core interactions (search, detail view, request creation, business verification, guidance) without unnecessary bloat. The count fits the standard 3-15 range comfortably.

Completeness4/5

The primary user journey (search → fetch → creer_demande) is fully supported, supplemented by company verification and targeted advice. Minor gaps exist, such as no update/cancel flow for requests, but these are not critical for the service's stated purpose.

Resources