RubiConnect

create_template

Create a message template in the account library (optionally organized inside a template folder via folderName or folderId, auto-creating the folder if needed). Supports rich standalone cards (with image/media, title, text, and buttons), carousels, media, and plain text. For WhatsApp agents, creates the template as DRAFT first in the workspace so the user can review it before submitting to Meta.

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>",
      "text": "<text>"
    },
    "name": "create_template"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes	Unique name of the template (lowercase, numbers, and underscores only for WhatsApp; descriptive name allowed for RCS).
`text`	Yes	Main message content or card description. Supports placeholders like {{name}} or {{first_name}}.
`type`	No	Template layout type: 'card' (rich standalone card with title/media/buttons), 'text' (plain text message), 'media' (standalone media with caption), or 'carousel' (multiple cards). If omitted, inferred from title/mediaUrl (defaults to 'card' if mediaUrl or title is provided, otherwise 'text').
`title`	No	Title for rich card templates.
`footer`	No	Optional footer text (WhatsApp supports up to 60 characters).
`agentId`	No	Agent ID or name this template belongs to. If omitted, uses active agent from context.
`content`	No	Optional raw template content object (e.g. { richCard: { ... } }). If provided, used directly.
`category`	No	Meta template category for WhatsApp agents (default 'MARKETING').	MARKETING
`folderId`	No	Optional existing template folder ID to place the template in.
`language`	No	Language code for WhatsApp templates, e.g. 'en_US', 'es_ES' (default 'en_US').	en_US
`mediaUrl`	No	Optional media header URL (image/video/document). For card templates, this is the card's hero image/video.
`folderName`	No	Optional template folder name to place the template in (automatically created if it does not exist yet).
`mediaHeight`	No	Height of the media component in a rich card ('SHORT', 'MEDIUM', 'TALL'). Default: 'MEDIUM'.	MEDIUM
`suggestions`	No	Optional list of interactive suggestion buttons.
`submitToMeta`	No	For WhatsApp agents: whether to submit immediately to Meta Graph API for approval. Defaults to false (draft-first mode). Only set to true if the user explicitly confirmed immediate submission.
`cardOrientation`	No	Card orientation for rich card templates ('VERTICAL' or 'HORIZONTAL'). Default: 'VERTICAL'.	VERTICAL

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 2, 2026

addedInput schema / properties / folderId

Added value: +{
+  "description": "Optional existing template folder ID to place the template in.",
+  "type": "string"
+}

addedInput schema / properties / folderName

Added value: +{
+  "description": "Optional template folder name to place the template in (automatically created if it does not exist yet).",
+  "type": "string"
+}

changedInput schema / properties / name / description

Previous value: -"Unique name of the template (lowercase, numbers, and underscores only)."New value: +"Unique name of the template (lowercase, numbers, and underscores only for WhatsApp; descriptive name allowed for RCS)."

First observedSep 15, 2026

TDQS

A3.6/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose genuinely non-obvious behavior: folders are auto-created when folderName is supplied, WhatsApp templates start as DRAFT, and submission to Meta is gated behind an explicit confirmation. It omits error/validation behavior (e.g. what happens on a duplicate name) and permission requirements.

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?

Three front-loaded sentences: purpose first, then supported layouts, then the WhatsApp draft caveat. No filler, though the layout enumeration partially restates the `type` enum and could be trimmed.

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 a 16-parameter creation tool with no annotations and no output schema, the description covers the important workflow behavior but says nothing about what comes back (template ID or object), nor how the created template relates to list_templates/get_template_detail for verification.

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% across all 16 parameters, so the schema already documents each field in depth, making 3 the baseline. The description only adds grouping context — that folderName/folderId organize into folders and that cards take image/media, title, text and buttons — without new syntax or constraints.

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 and resource ("Create a message template in the account library") and enumerates the layouts it supports. It implicitly separates itself from submit_template_to_meta by explaining the draft-first workflow, but never names the sibling or contrasts capabilities explicitly.

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?

Usage context is implied: for WhatsApp agents the template lands as a DRAFT for review, and submitToMeta should only be true on explicit user confirmation. There is no statement of when to prefer this over manage_templates or submit_template_to_meta, and no exclusions or prerequisites beyond that one caveat.

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

All RubiConnect 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?