Skip to main content
Glama
Upload-Post

Upload-Post

Official

Start an AutoDM or comment auto-reply

start_autodm

Monitor a post and auto-reply to matching commenters via Instagram DM or public replies elsewhere, after preview approval and optional keyword filtering.

Instructions

Watch one of the profile's posts and automatically answer everyone who comments on it (optionally only comments containing trigger_keywords, e.g. 'comment POST'). On Instagram (default) the answer is a private DM with reply_message and up to 3 link buttons. On tiktok, youtube, facebook, threads and bluesky it is a PUBLIC reply under each matching comment; links in TikTok replies are not clickable, so point people to the bio. Instagram and TikTok answer new comments within seconds; youtube, facebook, threads and bluesky check for them every monitoring_interval minutes (15 minimum). At most 25 replies per interval (10 on YouTube), and the monitor stops after 15 days. Returns the monitor ID used by the other AutoDM tools. For Instagram DMs on EVERY post of the account, story replies, story mentions or DM keywords, use create_autodm_rule instead: rules cover the whole account, never expire and work only through Instagram webhooks. 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": "start_autodm"
  }
}

Input Schema

NameRequiredDescriptionDefault
buttonsNoInstagram only: up to 3 web_url buttons ({ title, url }) added to each DM.
post_idNoPost to watch on tiktok/youtube/facebook/threads/bluesky (instead of post_url): TikTok video id, YouTube video id, Facebook post id ('{pageId}_{postId}'), Threads post id, Bluesky at:// URI. A TikTok or YouTube URL is also accepted.
platformNoNetwork of the post. Default instagram, which answers with a private DM. tiktok, youtube, facebook, threads and bluesky have no private reply to a comment, so matching comments get a PUBLIC reply under the comment instead.
post_urlNoPost URL to watch. Required on Instagram; on the other networks post_id is preferred.
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_messageYesText sent to matching commenters: a DM on Instagram, a public reply elsewhere.
reply_messagesNoPublic replies only: up to 5 alternative texts, rotated across comments so TikTok and YouTube do not see the same reply over and over.
profile_usernameYesUpload-Post profile name that owns the connected account.
trigger_keywordsNoKeyword or keywords; when set, only comments containing them are answered (case and accents ignored).
monitoring_intervalNoMinutes between comment checks. Minimum is 15. Instagram and TikTok answer within seconds, so there it only paces a backup check.

Output Schema

NameRequiredDescriptionDefault
resultNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.17.2

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the mutation/external-effect profile is covered, and the description adds substantial context beyond them: rate caps, monitor expiry, per-platform polling cadence, and the fact that nothing is sent without `confirmed`. However, the preview-without-confirmed behavior and the safety gate are behaviors the annotation set does not capture, and the description handles them well; the remaining gap is minimal. Score 4 would be tempting, but the tool is a long-running background monitor and the description does not say how to stop it or what happens to the monitor if the call is repeated.

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 paragraph is long but front-loaded and every sentence carries operational detail; there is no filler or restatement of the name. It would read better as short bullets separating platform behavior, limits, and the approval flow, but nothing is wasteful.

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 10-parameter, open-world monitor-creation tool with an output schema, the description covers what it does, per-platform semantics, rate limits, expiration, the approvable-preview gate, and the alternative tool. An agent has everything needed to call it correctly without guessing.

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 baseline is 3; the description nonetheless adds real meaning: `trigger_keywords` gets a usage example ('comment POST') and case/accent-insensitivity, `buttons` is scoped to Instagram DMs, `reply_messages` is explained as rotation to avoid repetition, and `confirmed` is tied to the preview/approval flow. The `post_id` vs `post_url` selection rule is also clarified beyond the schema wording.

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 opening sentence gives a specific verb and resource ('Watch one of the profile's posts and automatically answer everyone who comments'), and it explicitly names the sibling create_autodm_rule with the exact conditions that make that tool instead appropriate. An agent can distinguish this from delete_autodm, pause_autodm and public_reply_to_comment from the description alone.

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?

It states when to use this tool versus create_autodm_rule (per-post vs whole-account, expiring vs never-expiring, non-Instagram platforms), lays out per-platform behavior, and prescribes the two-step approval workflow (call without `confirmed` for a preview, then repeat with `confirmed: true`). It also gives explicit limits (25/interval, 10 on YouTube, 15-day expiry).

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