Skip to main content
Glama

Create campaign

create_campaign
Destructive

Create a campaign. The kind follows the inbox: a website inbox gets an ongoing campaign (the message is offered in the widget), an SMS inbox gets a one-off campaign sent at scheduled_at to the contacts of the labels in audience. No other inbox type is accepted: a WhatsApp campaign is composed by the administrator at Campaigns -> WhatsApp, because WhatsApp only allows approved templates. Call list_inboxes and list_labels first. This sends messages to real customers.

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": {
      "title": "<title>",
      "message": "<message>",
      "inbox_id": "<inbox_id>"
    },
    "name": "create_campaign"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
enabledNo
messageYes
audienceNoOne-off campaigns only: the labels whose contacts receive the message.
inbox_idYes
sender_nameNoWebsite campaigns only: the name the widget card shows as the speaker (for example "Ana"). Null clears it.
scheduled_atNoISO8601 time for a one-off campaign.
use_bot_identityNoWebsite campaigns only: speak as the inbox's AI agent, with its name and picture. Falls back to sender_name when the inbox has no AI agent.
trigger_only_during_business_hoursNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / sender_name
      Added value: +{
      +  "description": "Website campaigns only: the name the widget card shows as the speaker (for example \"Ana\"). Null clears it.",
      +  "maxLength": 40,
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedInput schema / properties / use_bot_identity
      Added value: +{
      +  "description": "Website campaigns only: speak as the inbox's AI agent, with its name and picture. Falls back to sender_name when the inbox has no AI agent.",
      +  "type": "boolean"
      +}
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false; the description corroborates and humanizes that with "This sends messages to real customers", and adds genuine behavioral context beyond annotations (message delivery model differs by inbox type: widget offer vs scheduled send to label contacts). It does not cover delivery timing for ongoing campaigns, permissions/authorization, or what happens on partial failure, so it stops short of a 5.

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 core action, then the environment-specific rules, then the prerequisite, then the impact warning — a sensible ordering. The run-on sentence about inbox kinds is dense but every clause carries decision-relevant information; nothing is filler.

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 create tool with nine parameters and no output schema, it covers what gets created, the branching type rule, prerequisites, and the real-world consequence. Gaps are the undocumented optional flags and no hint about the returned object (e.g., a campaign id to pass to delete_campaign or get_campaign), which an agent would reasonably want.

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 44%, and the description does add real meaning for the conditional core — audience is tied to one-off label targeting and scheduled_at to the one-off send time — but it says nothing about enabled, trigger_only_during_business_hours, title, or message, and never states that audience/scheduled_at become effectively required for SMS campaigns. Half the parameters remain unexplained in both places.

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 ("Create a campaign") and then defines the two accepted variants precisely: website inbox -> ongoing campaign offered in the widget, SMS inbox -> one-off campaign sent at scheduled_at. It also carves out the excluded case (WhatsApp campaigns are composed elsewhere), so an agent can tell this apart from create_voice_campaign / WhatsApp campaign tools without opening a schema.

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?

Gives explicit preconditions ("Call list_inboxes and list_labels first") and an explicit when-not (no other inbox type is accepted; WhatsApp is out of scope). The branching rule that selects ongoing vs one-off is stated outright rather than left to inference.

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.

Resources