Skip to main content
Glama

create_whatsapp_workflow

Create automated WhatsApp workflows triggered by message events, with actions like AI replies, standard responses, delays, and AI filters to manage customer interactions efficiently.

Instructions

Crear workflow de WhatsApp — Crea un nuevo workflow de automatizacion para respuestas de WhatsApp. Campos requeridos: name y actions. Si el usuario no especifica nombre, genera uno descriptivo automaticamente (ej: 'Respuesta IA fuera horario'). Si el usuario pide crearlo desactivado o para revision, usa status='disabled'. Por defecto se crea activo. LIMITE: maximo 10 workflows por tienda. Si recibes error de limite alcanzado, NO reintentes crear — en su lugar: 1) Llama a list_whatsapp_workflows para mostrar los existentes, 2) Sugiere al usuario eliminar workflows que ya no necesite o reutilizar uno existente con update_whatsapp_workflow. [mutation]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesNombre descriptivo del workflow (max 100 caracteres). Si el usuario no especifica, genera un nombre descriptivo automaticamente basado en las acciones/condiciones.
trigger_typeNoEvento que activa el workflow: 'message.received' (al recibir un mensaje, por defecto) o 'message.sent' (al enviar un mensaje)message.received
conditionsNoCondiciones para ejecutar el workflow. Formato: {logic: 'AND'|'OR', rules: [...]}. Si no se especifica, se ejecuta siempre.
actionsYesAcciones a ejecutar. Tipos: {type:'reply_with_ai'} o {type:'reply', message:'texto'} o {type:'delay', seconds:N} o {type:'ai_filter'} o {type:'ai_filter', prompt:'instrucciones adicionales'}. Para reply_with_ai se puede añadir pre_send_check:{enabled:true} para cancelar el envio si llega un mensaje nuevo durante la generacion IA. Para reply se puede añadir no_repeat:true y no_repeat_hours:N (1, 6, 24, 168 o 0=siempre) para no repetir al mismo contacto. ai_filter analiza si el mensaje necesita respuesta y detiene el workflow si no (previene bucles con mensajes tipo 'gracias' o 'vale', ideal como primera accion antes de reply_with_ai). Opcion prompt:'instrucciones adicionales' para personalizar criterios. Minimo una accion.
statusNoEstado inicial del workflow. Usar 'disabled' si el usuario quiere crearlo desactivado para revision. Por defecto: 'active'.active
session_idNoID de la sesion de WhatsApp a la que asignar este workflow. Si no se especifica (null), el workflow se ejecuta para todos los numeros conectados.
idNoID del workflow (si se especifica, actualiza en lugar de crear)
Behavior4/5

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

No annotations provided. Description discloses mutation behavior, creation limit (10 per store), error handling strategy, automatic name generation, and default status. Adequately covers behavioral aspects beyond the schema.

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?

Well-structured with logical flow, front-loaded main purpose. Some verbosity due to detailed parameter explanations, but justified by tool complexity (7 params, nested objects). Could be slightly more concise.

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?

No output schema exists, but description covers purpose, parameters, limits, error handling, and alternatives. For a creation tool, it's fairly complete. Lacks explicit return value description.

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

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3). Description adds significant value: explains action types (reply_with_ai, reply, delay, ai_filter) with detailed options like pre_send_check, no_repeat, and ai_filter prompt; clarifies conditions, status, session_id, and id for update. Goes far beyond schema.

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?

Description clearly states it creates a WhatsApp workflow for automation, specifies required fields (name and actions), mentions automatic name generation, and differentiates from sibling tools like list_whatsapp_workflows, update_whatsapp_workflow, and delete_whatsapp_workflow.

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?

Explicitly states when to use (to create a workflow), what to do if limit reached (call list_whatsapp_workflows and suggest deletion/reuse), default status, and when to use 'disabled'. Provides clear do-not-retry instruction on limit error.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wazionapps/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server