Skip to main content
Glama

Schedule several clips at once (Schedule all)

clipember_schedule_clips
Idempotent

Schedule all: turn several rendered clips (clip ids from clipember_get_clip_request, best first) into one post group each, to the same accounts, in the order given. mode=queue puts them in the queue: with step, the first clip goes out at step.startAt and each next one step.gapMinutes later (1440 = daily at the same time); without step, each takes the next free posting slot of the accounts (clipember_list_posting_slots; no slots → that clip is skipped with no_slots). mode=draft saves drafts (with step they keep those times) for the user to finish in the editor. Every target names its account (connectionId from clipember_list_platform_connections), each account once; leave captions out to let ClipEmber build each clip's caption from its AI title, description and hashtags. Each clip is checked on its own like clipember_create_post — on Free every clip counts as one video toward the monthly quota (drafts don't), locked accounts and expired clips are refused — and the result lists each clip. A clip that already has a draft, queued, published or unconfirmed post on one of these accounts is skipped (already_scheduled), so calling it twice does not duplicate. TikTok: no TikTok choice can be sent here — every TikTok post waits in the user's TikTok queue for their own choice; tell the user. mode=queue WILL publish publicly later — confirm clips, accounts and times with the user first.

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": {
      "clipIds": "<clipIds>",
      "mode": "<mode>",
      "targets": "<targets>"
    },
    "name": "clipember_schedule_clips"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYesqueue = schedule them; draft = save drafts without queuing
stepNoA fixed step between clips; left out = next free posting slots (queue) or drafts without a time
clipIdsYesRendered clips, in the order they should go out (1–50)
targetsYesThe accounts every clip goes to — one target per account, each with its connectionId

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / targets / items / properties / platform / enum
      Previous value: -[
      -  "tiktok",
      -  "youtube_shorts",
      -  "instagram_reels",
      -  "bluesky",
      -  "facebook_reels",
      -  "threads",
      -  "linkedin"
      -]New value: +[
      +  "tiktok",
      +  "youtube_shorts",
      +  "instagram_reels",
      +  "bluesky",
      +  "facebook_reels",
      +  "threads",
      +  "linkedin",
      +  "pinterest"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / targets / items / properties / caption / description
      Previous value: -"Final text for this platform, exactly as it should appear (no AI text is added). Limits: TikTok 2200, YouTube description 5000, Instagram 2200."New value: +"Final text for this platform, exactly as it should appear (no AI text is added). Limits: TikTok 2200, YouTube description 5000, Instagram 2200, LinkedIn 3000, Bluesky 300."
    • changedInput schema / properties / targets / items / properties / settings / description
      Previous value: -"YouTube, Instagram, Bluesky, Facebook Reels or LinkedIn options. Not for TikTok (use tiktokOptions) or Threads (Threads takes only the caption, ≤500 characters)."New value: +"YouTube, Instagram, LinkedIn or Bluesky options. Not for TikTok (use tiktokOptions)."
  3. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, the description explains how idempotency works through already_scheduled skips, how each clip is validated independently, how Free quota counting applies, and how locked or expired clips are refused. It also discloses the important public-publishing consequence of queue mode and the TikTok queue exception.

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 'Schedule all' and each sentence conveys a distinct rule, with little obvious filler. It is nevertheless a dense single paragraph with semicolon-heavy clauses, which makes scanning harder than it could 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?

Given the complex batch scheduling behavior, nested schema, annotations, and lack of an output schema, the description covers the important outcomes: per-clip checks, skipped clips, quota effects, draft versus queue behavior, and TikTok handling. Nothing critical for correct invocation appears 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?

Although schema coverage is 100%, the description adds meaningful operational semantics: step omission changes scheduling to next free slots, mode queue versus draft changes timing behavior, clipIds define ordering, and targets must name each account once. It also explains that omitting captions causes ClipEmber to build captions from AI metadata.

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: turn several rendered clips into one post group each, to the same accounts, in the given order. It also distinguishes the batch behavior from per-clip validation by referencing clipember_create_post.

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 clearly explains the two modes, with or without step, and notes that TikTok cannot be scheduled here and that queue mode should be confirmed with the user first. It references clipember_create_post and clipember_list_posting_slots, but does not explicitly contrast this with every relevant sibling such as single-post or series scheduling.

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