Skip to main content
Glama
Arsel MCP Server

Arsel MCP Server

Official
by Arsel-SA

Send WhatsApp Message

send-whatsapp
Destructive

Send one WhatsApp message from an approved template to a recipient, then confirm content and recipient first because sent messages cannot be recalled.

Instructions

Send one WhatsApp message from an approved template; WhatsApp allows no free text to start a conversation. Find templates and the parameters each needs with list-whatsapp-templates and get-whatsapp-template. Each message is charged to the organization's WhatsApp balance. This reaches real people, and a message that has gone out cannot be recalled. Before calling it, show the user what will go out and to whom, and wait for their go-ahead. See what was sent with list-whatsapp-messages.

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": {
      "to": "<to>",
      "template_name": "<template_name>"
    },
    "name": "send-whatsapp"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesRecipient in E.164 format, e.g. +966501234567.
languageNoTemplate language code; omit when only one approved template has this name.
parametersNoValues for the template placeholders, keyed by placeholder name. For an authentication template, the one-time code goes in `code`.
template_nameYesName of an `approved` template.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds context the annotations cannot: messages are billed to the organization's WhatsApp balance, no free-text first contact is possible, and a sent message cannot be recalled. The human-approval requirement is a meaningful operational constraint beyond the structured hints.

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?

The constraint and the required pre-call workflow are front-loaded, and each subsequent sentence adds a distinct fact: template discovery, billing, irreversibility, approval, and verification. No sentence merely restates the name or title.

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?

For a destructive, billed, outbound-messaging tool with no output schema, the description covers what matters: prerequisites (approved template, discovered parameters), cost, irreversibility, and the approval gate. Nothing an agent needs in order to call it safely is missing.

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 100%, so `to`, `language`, `parameters`, and `template_name` are already documented, giving a baseline of 3. The description earns an extra point by telling the agent where the `parameters` values actually come from (get-whatsapp-template) and by reinforcing the 'approved' requirement on template_name.

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 ('Send one WhatsApp message') plus a hard constraint ('from an `approved` template'), which immediately separates it from send-sms, send-push, and the campaign siblings. The 'one message' framing also signals this is not a bulk operation.

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 routes the agent to list-whatsapp-templates and get-whatsapp-template to obtain template names and their `parameters`, and to list-whatsapp-messages to verify delivery afterwards. It also imposes a concrete pre-call protocol: show the user the message and recipient, then wait for approval.

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