Skip to main content
Glama

Schedule post(s) for later

schedule_post

Schedule one or more text posts to be published at a future time on Threads, X (Twitter), and/or LinkedIn accounts. Threads posts can carry images from the media library via mediaIds on the first post: one image, or 2–20 images as a carousel; all target accounts must then be Threads accounts. TikTok Business supports one public video for one account with one caption: video takes an uploaded mediaId, requestId UUID, and privacyLevel PUBLIC_TO_EVERYONE. get_publish_status tracks TikTok publishing by the returned jobId, and repeating a request with the same requestId returns the same job. Instagram takes instagram with one account, a requestId UUID, FEED (1–20 media items), REELS (1 item), or STORIES (1 item), and uploaded mediaIds; it cannot be combined with posts or video. Caption is optional except that STORIES rejects it, and shareToFeed is REELS-only. Instagram publishing is asynchronous. YouTube takes youtube with one account, a requestId UUID, an uploaded video mediaId, a title (1–100 characters), optional description, privacyStatus (public, unlisted, or private), and optional madeForKids; it cannot be combined with posts, video, or instagram. get_publish_status tracks the returned jobId, and repeating a request with the same requestId returns the same job. A Facebook Page takes facebook with one account, a requestId UUID, and explicit FEED, REELS, or STORY content type. FEED accepts text and up to 10 uploaded media items, REELS requires one video, and STORY requires one image or video and rejects message. Facebook scheduling is asynchronous. Multiple posts are chained as a thread on Threads/X at the scheduled time. LinkedIn is single-caption only — it does not support chaining, so sending more than one post to a LinkedIn account is rejected. Supports up to 5 accounts at once. For X, links (http://, https://, www., and bare domains such as foo.io/path) are automatically removed from posts[0] before saving the schedule. Replies in posts[1+] and other platforms keep their links. Character limits apply after removal; an empty first X post rejects the entire request with VALIDATION_ERROR. Character limits: Threads 500, X 280 (25000 for Premium), LinkedIn 3000. The target workspace is determined automatically from accountIds (each account belongs to exactly one workspace); all accountIds must belong to the same workspace. cancel_scheduled_post cancels a schedule until processing starts; media schedules cannot be canceled once processing begins.

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": {
      "accountIds": "<accountIds>",
      "scheduledAt": "<scheduledAt>"
    },
    "name": "schedule_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
postsNoText posts to schedule. Required for text and TikTok modes; omit for Instagram, YouTube, or Facebook. If multiple, they are published as a thread chain at the scheduled time. Max 25 items. For X, links (http://, https://, www., and bare domains such as foo.io/path) are automatically removed from posts[0] before saving the schedule. Replies in posts[1+] and other platforms keep their links. Character limits apply after removal; an empty first X post rejects the entire request with VALIDATION_ERROR.
videoNoTikTok Business video: an uploaded mediaId and requestId UUID, one account and one caption, and explicit PUBLIC_TO_EVERYONE privacy.
youtubeNoYouTube video: one account, a requestId UUID, an uploaded video mediaId, a title, optional description, privacyStatus public/unlisted/private, and optional madeForKids. Cannot be combined with posts, video, or instagram.
facebookNoFacebook Page post: one account, a requestId UUID, explicit FEED/REELS/STORY content type, optional FEED/REELS message, and uploaded media IDs. STORY does not accept message.
mediaIdsNoThreads only: image mediaIds from the media library (list_media with mediaType IMAGE, or uploaded images) attached to posts[0]. One image makes an image post; 2–20 images make a carousel. Replies in posts[1+] stay text. Every accountId must be a Threads account. Cannot be combined with video, instagram, youtube, or facebook.
timezoneNoIANA timezone name (e.g. 'Asia/Seoul', 'America/New_York'). If omitted, the workspace default timezone is used.
instagramNoInstagram media post: one account, a requestId UUID, FEED/REELS/STORIES content type, and 1–20 uploaded media IDs. Cannot be combined with posts or video.
accountIdsYesAccount IDs to schedule the post for (from list_accounts). 1–5 accounts. Each must be a UUID.
scheduledAtYesFuture ISO 8601 timestamp with timezone offset at which to publish (e.g. '2026-06-15T09:00:00+09:00'). Must be in the future. list_workspaces returns each workspace's timezone for converting local times such as 'tomorrow 10am'.
workspaceIdNoOptional. The target workspace is determined automatically from accountIds; when given, it must match the accounts' workspace.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / instagram / description
      Previous value: -"Instagram media post: one account, a requestId UUID, FEED/REELS/STORIES content type, and 1–10 uploaded media IDs. Cannot be combined with posts or video."New value: +"Instagram media post: one account, a requestId UUID, FEED/REELS/STORIES content type, and 1–20 uploaded media IDs. Cannot be combined with posts or video."
    • changedInput schema / properties / instagram / properties / items / description
      Previous value: -"Ordered media items. FEED accepts 1–10; REELS and STORIES require exactly 1."New value: +"Ordered media items. FEED accepts 1–20; REELS and STORIES require exactly 1."
    • changedInput schema / properties / instagram / properties / items / maxItems
      Previous value: -10New value: +20
  2. Changed1 schema field changed
    • addedInput schema / properties / mediaIds
      Added value: +{
      +  "description": "Threads only: image mediaIds from the media library (list_media with mediaType IMAGE, or uploaded images) attached to posts[0]. One image makes an image post; 2–20 images make a carousel. Replies in posts[1+] stay text. Every accountId must be a Threads account. Cannot be combined with video, instagram, youtube, or facebook.",
      +  "items": {
      +    "format": "uuid",
      +    "type": "string"
      +  },
      +  "maxItems": 20,
      +  "minItems": 1,
      +  "type": "array"
      +}
  3. First observed

TDQS

A3.8/5.0
Behavior5/5

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

Beyond the annotations, the description discloses substantial behavior: asynchronous Instagram/Facebook publishing, requestId idempotency for media modes, X link stripping, character limits, workspace consistency from accountIds, and cancellation limits. The idempotentHint=false annotation is not contradicted because requestId idempotency applies only to specific media modes, while the tool overall creates new schedules.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph that repeats many schema-level details, such as YouTube title and description limits, Instagram item counts, and Facebook content-type specifics. It front-loads the purpose, but the mode-by-mode rules are hard to scan and could be shortened or structured.

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 10-parameter, nested, multi-platform scheduling tool with no output schema, the description covers most operational requirements, including job tracking and cancellation caveats. Gaps remain around return values for plain text schedules and how timezone interacts with scheduledAt, though the schema covers the latter.

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 description coverage is 100%, so the baseline is 3. The description adds meaningful cross-parameter rules not fully captured by individual schema fields, including platform-specific mutual exclusions, Threads-only mediaIds, LinkedIn single-post rejection, and the five-account limit. It omits the timezone parameter, but the schema already documents it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific verb and resource: scheduling one or more text posts for future publication on Threads, X, and/or LinkedIn. The future-time scope implicitly distinguishes it from immediate-publish siblings, but it never explicitly names publish_post as the alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives detailed mode-level constraints, such as which platforms accept media and which fields cannot be combined, and references get_publish_status and cancel_scheduled_post. However, it does not explicitly say when to choose schedule_post over publish_post or list_scheduled_posts, leaving high-level tool selection implied.

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