Skip to main content
Glama

schedule_post

Schedule a post for a date and time the user names, on one or more platforms. For the next free time in the posting schedule, use queue_post instead; to post right now, publish_post. When a platform has more than one connected account, pass platform_account_ids to pick one (list_connected_accounts gives the ids). If posting-time variance is on, the time is moved by up to half that window so posts don't all land on the exact minute, and the reply says so; pass variance_minutes: 0 for an exact time. All or nothing: if any channel can't be booked, nothing is saved and the error says why. With no scheduled_at, a penciled draft is booked at its penciled time if that is still ahead. Drafts never post. A penciled time only holds the slot. A time within 15 minutes of now books nothing: the reply carries a link the user must open to confirm it. Show the user the link; don't try to confirm it yourself.

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": {
      "id": "<id>"
    },
    "name": "schedule_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesPost ID to schedule
platformsNoPlatforms (defaults to post's existing platforms). Instagram needs an image or video on the post: if it has none, add one with `update_draft` (`images`) first.
workspaceNoOptional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that.
scheduled_atNoISO 8601 datetime (e.g. '2025-03-10T09:00:00Z'). Required unless the post is a draft penciled in for a time still ahead, which is then used.
variance_minutesNoOptional override for the account's posting-time variance window, 0-60. The stored time is jittered by up to half of it. 0 stores the exact time you asked for.
platform_account_idsNoOptional map of platform => connected_account_id (numeric id from `list_connected_accounts`). Example: {"twitter": 42} to post to the Twitter account with id 42. Each id must belong to the current account and match the platform.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / workspace
      Added value: +{
      +  "description": "Optional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare write/non-destructive/open-world; the description goes well beyond that with atomicity ("All or nothing: if any channel can't be booked, nothing is saved"), time jitter with the stored-time consequence, and the near-now rule that books nothing and returns a confirmation link the user must open. That last point is real workflow-shaping context an agent could not infer. Minor gap: nothing said about idempotency or what happens on retry after a partial-name-vs-id mismatch, keeping it just under a 5.

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?

Purpose and sibling routing are front-loaded, then edge cases in descending order of likelihood, which is the right structure. A couple of short lines are near-duplicative ("Drafts never post. A penciled time only holds the slot.") and the penciled-draft sentence is the least parseable part of an otherwise tight description.

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 6-parameter mutation with nested objects and no output schema, everything an agent needs is present: when to use it versus its two siblings, how to resolve accounts, how variance affects the stored time, the atomic failure mode, and the confirmation-link handoff. Nothing material is deferred to guesswork.

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 earns an increment by tying `platform_account_ids` to list_connected_accounts and the multi-account case, explaining `variance_minutes: 0` as the exact-time escape hatch, and clarifying that omitting `scheduled_at` is legal only for penciled drafts still in the future. Those are usage semantics rather than restatements of the field docs.

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 clause states a specific verb and resource ("Schedule a post") plus the scope ("a date and time the user names, on one or more platforms"), which immediately separates it from queue_post (next free slot) and publish_post (now). An agent can route correctly without opening any 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?

It names both alternatives explicitly with the condition that selects each: use queue_post for the next free time, publish_post to post right now. It also spells out the sub-case where scheduled_at is omitted and the draft carries a penciled time, so the boundary between the three scheduling paths is unambiguous.

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