Skip to main content
Glama

Launch a WhatsApp campaign

campaign_launch
Destructive

Starts sending a DRAFT WhatsApp campaign, or resumes a PAUSED one; this messages every recipient. With dryRun: true it returns the recipient count, the template and its Meta approval status, and the sending number, and sends nothing. Refused if the template is not approved by 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": {
      "campaignId": "<campaignId>"
    },
    "name": "campaign_launch"
  }
}

Input Schema

NameRequiredDescriptionDefault
dryRunNoIf true, preview who would be messaged without sending
campaignIdYesThe campaign's id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / campaignId / description
      Previous value: -"The campaign_id from campaign_create or campaign_list"New value: +"The campaign's id"
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag destructive/open-world/non-idempotent, and the description adds real context beyond them: the blast reaches every recipient, dryRun sends nothing and returns recipient count, template and Meta approval status, and the sending number, and the template-approval precondition can block the call. It stops short of saying what happens to the campaign state after launch or whether a partial send can occur.

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 compact clauses: what it does, then the dryRun path, then the refusal condition. The action and its blast radius are front-loaded and nothing is redundant.

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 destructive, non-idempotent launch with no output schema, it covers preconditions, side effects, and preview behavior well. It does not explain post-launch state, reversibility, or how to stop an in-flight campaign, which an agent committing to an irreversible send would benefit from.

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 the two parameters are already documented, but the description adds meaning the schema lacks: dryRun is not merely a preview flag, it returns specific preview data (recipient count, template, approval status, sending number).

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?

The description uses a specific verb (starts sending / resumes) with a specific resource (DRAFT or PAUSED WhatsApp campaign), and the state-machine framing implicitly separates it from campaign_create and campaign_pause.

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

Usage Guidelines4/5

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

It makes the preconditions explicit: only works on DRAFT or PAUSED campaigns, is refused if the template is unapproved, and dryRun is the way to preview. It does not name campaign_pause or campaign_detail as the alternative path, but the operative conditions for choosing this tool are clear.

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.