Skip to main content
Glama
Upload-Post

Upload-Post

Official

Create an account-wide Instagram AutoDM rule

create_autodm_rule

Create a persistent Instagram auto-DM rule that replies to every comment on any post or reel, story replies, story mentions, or keyword DMs. Preview first, then confirm to activate.

Instructions

Create a rule that AUTOMATICALLY sends private Instagram DMs as the user, with nobody reviewing each message, to everyone who triggers it on the whole Instagram account: comments on ANY post or reel (present and future), and optionally replies to the account's stories, mentions of the account in other people's stories, and DMs containing a keyword. Unlike start_autodm (one post, stops after 15 days), a rule never expires: it runs until paused or deleted. Use it when the user wants 'every post', stories or DM keywords; use start_autodm for a single post. triggers: 'comment' (default), 'story_reply', 'story_mention', 'dm_keyword' (needs trigger_keywords, otherwise every DM would be answered). trigger_keywords limit comment, story-reply and DM triggers to messages containing them (case and accents ignored); a story mention has no text, so keywords do not apply to it. Limits: up to 10 rules per Instagram account; at most 25 DMs per account every 15 minutes and the plan's daily DM allowance (what does not fit is queued and sent later, within Instagram's reply windows); one DM per comment; each person gets at most one DM per rule every per_user_cooldown_hours (default 24; story and DM triggers never less than 24). Replies inside a thread, the account's own comments and live-video comments are not answered. A post with its own active start_autodm monitor is handled by that monitor, not by the rule. Works only through Instagram webhooks (no polling): creating a rule subscribes the account to them, and if Instagram refuses, no rule is created and the call returns 502 webhook_subscription_failed (the user must reconnect Instagram). Other errors: 409 duplicate_rule, rule_limit_reached or rule_creation_in_progress; 503 account_rules_disabled. Instagram only. Needs the user's approval: call it first without confirmed to get a preview (nothing is sent), show the user exactly what will go out, and repeat the call with confirmed: true only after they approve.

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": {
      "profile_username": "<profile_username>",
      "reply_message": "<reply_message>"
    },
    "name": "create_autodm_rule"
  }
}

Input Schema

NameRequiredDescriptionDefault
buttonsNoUp to 3 web_url buttons ({ title, url }) added to each DM.
triggersNoWhat starts a DM. Default ['comment']. 'dm_keyword' requires trigger_keywords.
confirmedNoSet to true only after the user has seen the preview this tool returns without it and approved it. Without it nothing is sent.
reply_messageYesDM text sent to whoever triggers the rule. Up to 1000 characters, or 640 when `buttons` are set.
profile_usernameYesUpload-Post profile name that owns the connected Instagram account.
trigger_keywordsNoKeyword or keywords (up to 20). When set, only comments, story replies and DMs containing one of them are answered.
per_user_cooldown_hoursNoWhole hours before the same person can get this rule's DM again, 0-720. Default 24. Story and DM triggers always wait at least 24.

Output Schema

NameRequiredDescriptionDefault
resultNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.23.0

TDQS

A4.9/5.0
Behavior5/5

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

Far exceeds what the annotations convey (readOnly=false, destructive=false, openWorld=true, idempotent=false). It discloses rate limits (25 DMs per 15 minutes plus the plan's daily allowance with queueing), a cap of 10 rules per account, per-user cooldown floors, non-expiry, exclusions (thread replies, own comments, live-video comments), the webhook dependency and its 502 failure mode, and concrete error codes (409 duplicate_rule, rule_limit_reached, rule_creation_in_progress, 503 account_rules_disabled).

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 highest-signal facts (what it does, scope, contrast with start_autodm, preview flow) and nearly every clause carries operational information. However, it is a single dense paragraph covering triggers, limits, exclusions, errors and approval, which is harder to scan than a bulleted layout would be.

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 high-blast-radius automation tool with 7 parameters, it covers scope, trigger semantics, throttling, failure modes, platform restriction, and the two-step confirmation requirement. An output schema exists, so the preview return value needs no explanation, and nothing an agent needs to call this correctly appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, yet the description adds meaning the schema cannot: which triggers keywords actually filter ('comment, story-reply and DM triggers', explicitly not story mentions because they carry no text), the reason dm_keyword requires trigger_keywords ('otherwise every DM would be answered'), and the hard 24-hour floor overriding per_user_cooldown_hours for story and DM triggers.

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 and resource ('Create a rule that AUTOMATICALLY sends private Instagram DMs') and immediately scopes it as account-wide across all present and future posts and reels. It explicitly contrasts with the sibling start_autodm (one post, 15-day expiry) versus a rule that never expires, so an agent can route correctly without opening either 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 selection criteria: 'Use it when the user wants every post, stories or DM keywords; use start_autodm for a single post.' It also states platform restriction ('Instagram only'), the required preview-then-confirm workflow, and the precedence case where an active start_autodm monitor on a post wins over the rule.

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