Skip to main content
Glama
kadenzo-mcp

kadenzo-mcp

by Kadenzo

create_dm_automation

Create Instagram and Facebook DM automation rules for comment keywords, DM keywords, story replies, default replies, or campaign links; replies are paced by the platform.

Instructions

Create a DM automation rule. trigger_type: comment_keyword (comment → DM; REQUIRES opening_message + button_label — Meta's two-step opt-in, enforced), dm_keyword, story_reply_keyword, default_reply, or ref_link (campaign DM link; Instagram requires conversation starters on the account, verified at create — a 502 means the check could not run, retry). Sending always goes through the platform's pacing engine; there is no send-a-DM-now tool.

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": {
      "platform": "<platform>",
      "account_id": "<account_id>",
      "trigger_type": "<trigger_type>"
    },
    "name": "create_dm_automation"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
activeNoDefault true. Set false to create paused.
keywordsNoTrigger keywords (required for *_keyword triggers; the campaign name for ref_link).
platformYes
ai_promptNoInstructions for AI replies.
account_idYesAccount id from list_accounts.
ai_enabledNoAI-composed replies (not for comment_keyword). Requires ai_prompt.
match_typeNoDefault "contains".
button_labelNocomment_keyword: the opt-in button text. Required for comment_keyword.
trigger_typeYes
reply_variantsNoDM reply message(s) — one is rotated per send. Required unless ai_enabled.
opening_messageNocomment_keyword: the opt-in DM shown with the button. Required for comment_keyword.
once_per_user_hoursNoPer-person cooldown in hours. 0 disables.
public_reply_variantsNocomment_keyword only: public comment replies (e.g. "Check your DMs!").

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.4.4

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and discloses important details: Meta's enforced two-step opt-in for comment_keyword, Instagram conversation-starter validation at create time, 502 retry guidance, and that sending always goes through the platform's pacing engine. It does not cover permissions or the success return value, leaving a few gaps.

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?

The description is front-loaded with the purpose and contains no filler. The second sentence is dense and semicolon-heavy, which slightly reduces scanability, but every clause carries useful operational information for a 14-parameter tool.

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 14-parameter creation tool with no annotations and no output schema, the description covers the important trigger-specific invocation rules and platform constraints. It omits return behavior and permission requirements, which would be helpful given the absence of an output schema, but the core call guidance is complete.

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 79% and the schema already documents many parameters, but the description adds cross-field trigger semantics beyond the schema: comment_keyword requires both opening_message and button_label, ref_link is a campaign DM link with an Instagram account prerequisite, and trigger_type values have behavioral implications. It still does not explain every parameter, but it meaningfully supplements the schema.

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 states a specific verb and resource: 'Create a DM automation rule.' It immediately scopes the tool to automation-rule creation, which distinguishes it from sibling tools like update_dm_automation, delete_dm_automation, and list_dm_automations.

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 gives clear context for choosing trigger types and states key constraints, such as comment_keyword requiring opening_message and button_label, and ref_link requiring Instagram conversation starters. It does not explicitly contrast create with update, but the creation purpose is unambiguous and the note that there is no send-a-DM-now tool helps set expectations.

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