Skip to main content
Glama
Sign In

SupaBird

by io.supabird.api
OverviewDiscussionsAdmin

Schedule Saved Post

schedule_saved_post

Schedule one of the user's existing drafts or saved ideas on X, by its id from get_drafts or get_saved_ideas. Optionally cross-post to LinkedIn, Threads, BlueSky, Instagram, and/or TikTok.

  • The same post is scheduled in place, as in the SupaBird app. It keeps its text, images, video, and thread parts, and leaves Drafts / Saved. Do not pass new text; to change the text, use schedule_post with the new text instead.

  • Pass scheduled_date (ISO 8601, in the future), or next_free_slot: true to use the user's next free posting slot (today plus the next 7 days, skipping slots that already have a post). Confirm the time with the user when they did not give one.

  • Templates, posts that are already scheduled, published posts, trash, and Content Machine items cannot be scheduled with this tool. For an already scheduled post, unschedule_post first if the user wants a new time. For a Content Machine item, write an original post from it, then use schedule_post.

  • Cross-posting works like schedule_post: default is X only; only add also_post_to when the user asked. Instagram requires an image or video. TikTok requires a video or photo.

  • TikTok: before posting there, ASK the user who can see it (everyone, friends, followers, or only them) and whether it promotes their brand or is a paid partnership, and tell them "By posting, you agree to TikTok's Music Usage Confirmation". Pass their answers in tiktok. Never choose the visibility for them. TikTok can take a few minutes to process before the post shows on their profile.

  • After a successful publish, show published_urls as clickable links. To cancel later, use unschedule_post with the returned post_id.

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": {
      "post_id": "<post_id>"
    },
    "name": "schedule_saved_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
tiktokNoRequired when TikTok is in also_post_to. Ask the user first; without it TikTok is skipped.
post_idYesThe `id` of the draft or saved idea from get_drafts or get_saved_ideas. Mongo ObjectId string.
post_to_xNoPost to X. Defaults to true. Set false only when the user wants other networks and explicitly not X.
also_post_toNoExtra networks besides X: 'linkedin', 'threads', 'bluesky', 'instagram', 'tiktok', and/or 'all'. Omit for X-only. Only set this when the user asked to cross-post. Instagram requires an image or video. TikTok requires a video or photo.
next_free_slotNoSet true to schedule at the user's next free posting slot instead of scheduled_date. Fails if the user has no free slot in the next 8 days.
platform_textsNoOptional per-network captions for the other networks when the post's text is too long or should differ.
scheduled_dateNoISO 8601 date-time for when the post should publish (e.g. '2026-03-05T14:30:00.000Z'). Must be in the future. Required unless next_free_slot is true.
threads_topic_tagNoOptional Threads topic tag (without #). Ignored unless Threads is in also_post_to.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnly=false, destructive=false, openWorld=true, so the description carries real behavioral weight and does: the post is scheduled in place, retains text/media/thread parts, and leaves Drafts/Saved. It adds operational traits annotations cannot express — TikTok processing latency, mandatory visibility/partnership questions, and a legal notice the agent must surface before posting.

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 lead sentence followed by tight bullets, each covering a distinct failure mode or precondition. A few lines restate what the schema already says (the TikTok visibility/partnership questions, the Instagram/TikTok media requirements), costing some economy on an otherwise well-structured definition.

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 an 8-parameter, nested-object mutation tool with no output schema, the description covers prerequisites, validation constraints, network-specific requirements, async behavior, and the return surface ("show published_urls as clickable links", "use unschedule_post with the returned post_id"). An agent has everything needed to invoke and follow up correctly.

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 the baseline is 3, but the description adds genuine semantics: next_free_slot means the user's next free slot within today plus 7 days skipping occupied slots, and scheduled_date must be a future ISO 8601 value. It omits platform_texts, post_to_x, and threads_topic_tag entirely, leaving those to the schema, which keeps it from a 5.

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?

States a specific verb and resource ("Schedule one of the user's existing drafts or saved ideas on X") plus identifying input source ("by its `id` from get_drafts or get_saved_ideas"). It explicitly distinguishes itself from the near-sibling schedule_post ("Do not pass new text; to change the text, use schedule_post"), 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 exclusions (templates, already-scheduled posts, published posts, trash, Content Machine items) and names the correct alternative for each case (unschedule_post first; write an original post then schedule_post). It also states the default (X only) and the condition for adding cross-posting ("only add also_post_to when the user asked").

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

All SupaBird toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources