neuron

Compose Message

neuron_compose_message

Compose and send a new message to a phone number via a specific channel. Automatically creates a new conversation if one does not exist.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	Yes	Recipient phone number (E.164 format, e.g., '2348012345678')
`text`	No	Message text content (optional when sending a template)
`sendAt`	No	ISO 8601 date-time for scheduled delivery (e.g., '2025-12-31T10:00:00Z'). Message sends immediately if omitted.
`mediaUrl`	No	URL of media to attach (required for non-text message types)
`template`	No	Approved template (official WhatsApp Business API sessions only). Required to reach anyone who hasn't messaged you in the last 24 hours. Set messageType to 'template'.
`channelId`	Yes	Unique identifier (UUID) of the WhatsApp channel to send through
`contactName`	No	Display name for the recipient contact
`messageType`	No	Type of message: 'text' (default), 'image', 'document', or 'template' (official API sessions)

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 7, 2026

changedInput schema / properties / messageType / description

Previous value: -"Type of message: 'text' (default), 'image', or 'document'"New value: +"Type of message: 'text' (default), 'image', 'document', or 'template' (official API sessions)"

addedInput schema / properties / template

Added value: +{
+  "additionalProperties": false,
+  "description": "Approved template (official WhatsApp Business API sessions only). Required to reach anyone who hasn't messaged you in the last 24 hours. 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 / properties / text / description

Previous value: -"Message text content"New value: +"Message text content (optional when sending a template)"

changedInput schema / required

Previous value: -[
-  "channelId",
-  "to",
-  "text"
-]New value: +[
+  "channelId",
+  "to"
+]

Changed1 schema field changedJul 25, 2026

addedInput schema / properties / sendAt

Added value: +{
+  "description": "ISO 8601 date-time for scheduled delivery (e.g., '2025-12-31T10:00:00Z'). Message sends immediately if omitted.",
+  "type": "string"
+}

First observedJun 28, 2026

TDQS

B3.3/5.0

Behavior3/5

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive, closed-world mutation. The description adds one genuinely useful side effect beyond the annotations: it automatically creates a conversation if none exists. It does not cover failure behavior, session/template-window implications, or scheduling interactions beyond what the schema states.

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?

Two tightly written sentences with zero filler, and the core action is front-loaded ahead of the side-effect detail. Nothing could be trimmed without losing meaning.

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

Completeness3/5

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

For an 8-parameter mutation tool with a nested template object and no output schema, the description is minimal. The schema carries parameter detail but the description omits return/failure behavior and, more importantly, any routing guidance among the numerous sibling send tools.

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 all 8 parameters, including the template object and its nested fields. The description adds no parameter-level detail beyond what the schema provides, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('compose and send a new message') plus the target ('phone number via a specific channel'), which is clear on its own. However, it does not distinguish this from close siblings like neuron_send_message, neuron_send_whatsapp, or neuron_bot_api_send, leaving the agent to guess which send path applies.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus the many alternative send tools (send_message, send_whatsapp, bot_api_send, send_campaign_message). The auto-conversation-creation clause hints at a scenario but does not frame it as a selection rule or exclusion.

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

All neuron tools Inspect

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

Need Help?