Skip to main content
Glama
Sign In
Arsel MCP Server

Arsel MCP Server

Official
by Arsel-SA
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Create WhatsApp Template

create-whatsapp-template
Destructive

Create a WhatsApp template and submit it to Meta for review in one call, so your business can start approved conversations with customers.

Instructions

Create a WhatsApp template and submit it to Meta for review, in one call. WhatsApp only lets a business start a conversation with an approved template.

The template goes to Meta as written and this server cannot withdraw it, so before calling you MUST show the user the exact content and get their go-ahead. The organization needs a connected WhatsApp Business account, which is set up in the Arsel dashboard.

marketing and utility templates take components. authentication templates take authentication instead, and no components.

The template comes back pending. Review usually takes minutes and can take up to 48 hours, so check on it later with get-whatsapp-template rather than polling. Name and language identify a template: repeating a create that already succeeded is refused.

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>",
      "language": "<language>",
      "category": "<category>"
    },
    "name": "create-whatsapp-template"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesLowercase letters, digits and underscores, starting with a letter, e.g. order_shipped. Unique per language.
categoryYes
languageYesMeta language code, e.g. en, ar or en_US.
componentsNoThe template content in Meta's component format, with `type`, `format` and button `type` in uppercase. Placeholders are named in lowercase snake_case, e.g. `{{first_name}}`: numbered ones such as `{{1}}` are refused, and a name can be used in the header or the body, not both. Example: [{"type":"HEADER","format":"TEXT","text":"Your order"},{"type":"BODY","text":"Hi {{first_name}}, order {{order_id}} has shipped."},{"type":"FOOTER","text":"Acme Store"},{"type":"BUTTONS","buttons":[{"type":"URL","text":"Track","url":"https://example.com/track"}]}]
authenticationNoThe options of a one-time-code template. Meta fixes its wording, so there is no content to write; the code itself is supplied when the message is sent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare destructive=true, idempotent=false and readOnlyHint=false; the description supplies the substance behind them — the submission goes to Meta as written and cannot be withdrawn by this server, the template returns as pending with a review window of minutes to 48 hours, and a repeat create with the same name+language is refused. That is real operational context an agent cannot infer from the annotation flags.

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?

Front-loaded with the action and its irreversible consequence, then prerequisites, then the category branching rule, then the follow-up path — a sensible ordering. Slightly long for four short paragraphs, and the category paragraph partly restates schema enum structure, but no sentence is pure filler.

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

Completeness5/5

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

Covers what an agent needs for a destructive, non-idempotent, human-approval-gated mutation with no output schema: approval requirement, account prerequisite, category-driven shape, async review outcome, deduplication behavior, and the follow-up tool. Nothing material is left ambiguous.

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 already 80%, but the description adds a cross-parameter constraint the schema does not encode: marketing and utility templates take components, authentication templates take authentication instead and no components. It also clarifies that name plus language identify a template, explaining why both are required. It adds little beyond the schema on individual nested fields (placeholders, button types), which are already documented.

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?

Opens with a specific verb+resource+side effect: create a WhatsApp template and submit it to Meta for review in one call. It also states the underlying constraint (conversations require an approved template) so the agent understands why this tool exists, which distinguishes it from sibling reads like get-whatsapp-template and list-whatsapp-templates.

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?

Explicit preconditions and exclusions: the agent MUST show the user exact content and get approval before calling, and the organization needs a connected WhatsApp Business account set up in the Arsel dashboard. It also names the alternative workflow — check status later with get-whatsapp-template rather than polling — and routes category selection (marketing/utility vs authentication).

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

Deploy Server

Other Tools