Skip to main content
Glama

Ficiel MCP

by io.ficiel
OverviewDiscussionsAdmin

Créneaux libres de l'agenda

ficiel_get_slots
Idempotent

Lit les créneaux RÉELLEMENT libres de l'agenda connecté à Ficiel (GoHighLevel ou Google Agenda, page Intégrations), sur les 30 prochains jours et au moins 2 h après maintenant : 6 par défaut, répartis sur plusieurs jours (un par jour en partant du plus proche). Les disponibilités du prospect filtrent la liste : jours de la semaine, plage horaire (après, avant), date de début, nombre de jours. Avec lead_id, les créneaux rendus sont mis de côté 24 h pour ce contact : ils ne sont proposés à aucun autre contact pendant ce temps, et le même contact retrouve sa liste. Sans lead_id, rien n'est mis de côté. Sans agenda connecté, l'outil le dit et rend le lien de réservation s'il existe.

Input Schema

NameRequiredDescriptionDefault
apresNoLe créneau commence à cette heure ou après (HH:MM, fuseau de l'organisation).
avantNoLe créneau est fini à cette heure au plus tard (HH:MM).
nombreNoNombre de créneaux (1 à 20, 6 par défaut).
lead_idNoContact à qui les créneaux seront proposés : ils sont mis de côté 24 h pour lui.
nb_joursNoNombre de jours lus à partir du début (1 à 30, 30 par défaut).
date_debutNoPas avant ce jour (AAAA-MM-JJ, fuseau de l'organisation).
jours_semaineNoJours où le prospect est disponible : 1 = lundi … 7 = dimanche.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / apres
      Added value: +{
+  "description": "Le créneau commence à cette heure ou après (HH:MM, fuseau de l'organisation).",
+  "pattern": "^([01]\\d|2[0-3]):[0-5]\\d$",
+  "type": "string"
+}
    • addedInput schema / properties / avant
      Added value: +{
+  "description": "Le créneau est fini à cette heure au plus tard (HH:MM).",
+  "pattern": "^([01]\\d|2[0-3]):[0-5]\\d$",
+  "type": "string"
+}
    • addedInput schema / properties / date_debut
      Added value: +{
+  "description": "Pas avant ce jour (AAAA-MM-JJ, fuseau de l'organisation).",
+  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+  "type": "string"
+}
    • addedInput schema / properties / jours_semaine
      Added value: +{
+  "description": "Jours où le prospect est disponible : 1 = lundi … 7 = dimanche.",
+  "items": {
+    "maximum": 7,
+    "minimum": 1,
+    "type": "integer"
+  },
+  "maxItems": 7,
+  "minItems": 1,
+  "type": "array"
+}
    • addedInput schema / properties / lead_id
      Added value: +{
+  "description": "Contact à qui les créneaux seront proposés : ils sont mis de côté 24 h pour lui.",
+  "format": "uuid",
+  "type": "string"
+}
    • addedInput schema / properties / nb_jours
      Added value: +{
+  "description": "Nombre de jours lus à partir du début (1 à 30, 30 par défaut).",
+  "maximum": 30,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / nombre
      Added value: +{
+  "description": "Nombre de créneaux (1 à 20, 6 par défaut).",
+  "maximum": 20,
+  "minimum": 1,
+  "type": "integer"
+}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

The readOnlyHint=false annotation is reconciled by the description's explicit disclosure that lead_id causes a 24h hold, while calls without lead_id have no reservation side effect. It also explains external-calendar dependency and fallback behavior when no calendar is connected.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core operation and scope, then layers filtering, lead_id side effects, and no-calendar behavior. Despite being dense, every sentence adds operational information.

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?

For a 7-parameter tool with no output schema, it covers the main behavioral contract, filtering constraints, side effects, and no-calendar fallback. It stops short of describing the exact returned slot structure, which is the only notable gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 meaningful semantics beyond the schema: default 6 slots spread across days, the 30-day/2h-after-now window, and the cross-contact effect of lead_id holds. It does not add much detail beyond the schema for apres/avant, which keeps it at 4.

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 states a specific verb and resource: it reads the genuinely free slots of the connected calendar, with explicit scope (next 30 days, at least 2h from now). This clearly separates it from booking or mutation siblings such as ficiel_book_slot.

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?

It explains the two main usage modes: with lead_id the slots are held for that contact, without lead_id nothing is held, and it covers the no-connected-calendar case. It does not explicitly name ficiel_book_slot as the follow-up booking tool, so siblings still require inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ficiel MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources