Skip to main content
Glama

Create Broadcast

neuron_create_broadcast

Create a new broadcast message in draft status. Provide recipients directly or use recipientSources to resolve from contact lists. The WhatsApp channel is auto-resolved if not specified.

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": {
      "name": "<name>"
    },
    "name": "neuron_create_broadcast"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesDisplay name or label for the broadcast
botIdNoIdentifier (UUID) of a bot to send through. Each recipient's channel is picked by the bot's load-balancer + sticky sessions. Takes precedence over channelId.
messageNoMessage content to broadcast to recipients (optional when sending a template). {{first_name}} or {{name}} is replaced with each recipient's saved name, "there" when there is none; {{first_name|Customer}} picks that word.
mediaUrlNoURL of media to attach (required for image or document message types)
templateNoApproved template (official WhatsApp Business API sessions only). On official API sessions, use one for broadcasts: most recipients won't have messaged you in the last 24 hours, and only templates reach them. Set messageType to 'template'.
channelIdNoIdentifier (UUID) of the WhatsApp channel to send through (auto-resolved from default channel if omitted)
recipientsNoDirect list of recipients (alternative to recipientSources)
messageTypeNoType of message to send (e.g., 'text', 'image', 'document', or 'template' on official API sessions)
scheduledAtNoISO 8601 date-time for scheduled broadcast delivery (e.g., '2025-12-31T10:00:00Z'). Creates as draft if omitted.
recipientSourcesNoResolve recipients dynamically from contact lists with filtering and exclusion

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / message / description
      Previous value: -"Message content to broadcast to recipients (optional when sending a template)"New value: +"Message content to broadcast to recipients (optional when sending a template). {{first_name}} or {{name}} is replaced with each recipient's saved name, \"there\" when there is none; {{first_name|Customer}} picks that word."
  2. Changed4 schema fields changed
    • changedInput schema / properties / message / description
      Previous value: -"Message content to broadcast to recipients"New value: +"Message content to broadcast to recipients (optional when sending a template)"
    • changedInput schema / properties / messageType / description
      Previous value: -"Type of message to send (e.g., 'text', 'image', 'document')"New value: +"Type of message to send (e.g., 'text', 'image', 'document', or 'template' on official API sessions)"
    • addedInput schema / properties / template
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Approved template (official WhatsApp Business API sessions only). On official API sessions, use one for broadcasts: most recipients won't have messaged you in the last 24 hours, and only templates reach them. Set messageType to 'template'.",
      +  "properties": {
      +    "components": {
      +      "description": "Meta send-time components with variable values, e.g. [{ type: 'body', parameters: [{ type: 'text', text: 'Ada' }] }]. Omit for templates without variables.",
      +      "items": {
      +        "additionalProperties": {},
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "language": {
      +      "description": "Template language code, e.g. 'en_US'",
      +      "type": "string"
      +    },
      +    "name": {
      +      "description": "Template name exactly as approved (see neuron_list_whatsapp_templates)",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "name",
      +    "language"
      +  ],
      +  "type": "object"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "name",
      -  "message"
      -]New value: +[
      +  "name"
      +]
  3. Changed1 schema field changed
    • addedInput schema / properties / botId
      Added value: +{
      +  "description": "Identifier (UUID) of a bot to send through. Each recipient's channel is picked by the bot's load-balancer + sticky sessions. Takes precedence over channelId.",
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / scheduledAt
      Added value: +{
      +  "description": "ISO 8601 date-time for scheduled broadcast delivery (e.g., '2025-12-31T10:00:00Z'). Creates as draft if omitted.",
      +  "type": "string"
      +}
  5. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare a non-read-only, non-destructive, non-idempotent create operation, and the description adds meaningful behavior: the result is always a draft, the WhatsApp channel is auto-resolved when omitted, and templates are required on official API sessions because recipients likely fall outside the 24-hour window. It does not mention permission requirements or quota/rate behavior, but the draft-state and channel-resolution details go beyond 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.

Conciseness5/5

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

Three short sentences, front-loaded with the core action and draft state, followed by the recipient alternative and channel default. No filler or repetition.

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 10-parameter tool with nested recipient and template objects and no output schema, the description covers the most consequential behaviors: draft creation, recipient sourcing modes, and automatic channel resolution. The highly detailed schema fills in the remaining parameter semantics, so the definition is sufficient, though it could say more about when a draft becomes sendable.

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 description coverage is 100%, so the schema already documents every parameter including recipient objects, template components, scheduling, and channel selection. The description reinforces the recipients-vs-recipientSources alternative and channel auto-resolution, but adds little syntax or constraint detail beyond what the schema already provides; 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?

States a specific verb and resource ('Create a new broadcast message') plus a lifecycle qualifier ('in draft status') that separates it from neuron_send_broadcast and neuron_update_broadcast. An agent can identify both the action and the resulting state without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the two recipient-sourcing paths ('Provide recipients directly or use recipientSources to resolve from contact lists'), which is useful invocation guidance. However, it never states when to choose this tool over neuron_send_broadcast, neuron_update_broadcast, or how a created draft is later sent, leaving the tool-selection decision implicit.

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