Skip to main content
Glama

Schedule a post

schedule_post
Destructive

Give an existing draft (or approved post) a time. The post is validated for every account (all issues at once), checked against the key's caps and the X link allowance, and — when the workspace requires approval — must be APPROVED with unchanged content. schedule_at is ISO 8601 with an offset; the workspace timezone is used for display. Each account then publishes at its own staggered time (stagger_min/max_seconds on the post), plus its per_channel.delay_minutes when the post gives a network a later time. More than 10 accounts or a start within 60 minutes needs confirmation_token from the returned plan: without it you get needs_confirmation and details.plan (accounts by network, first and estimated last dispatch, X link-post cost, TikTok notes) to show your human. The post then goes out publicly on the person's real accounts: only schedule when your human asked to publish it. Scheduling needs the publish scope and a claimed sandbox. To move a scheduled post, call schedule_post again with the new time; cancel_post stops it.

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": {
      "workspace_id": "<workspace_id>",
      "post_id": "<post_id>",
      "schedule_at": "<schedule_at>"
    },
    "name": "schedule_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoDeprecated boolean; does not bypass confirmation. A confirmation_token is required when a schedule goes to more than 10 accounts, starts within 60 minutes, or includes a Pinterest account. Without it you get needs_confirmation with the dispatch plan and confirm_url, where your human approves it in Shager; then resend the same call.
post_idYes
schedule_atYesISO 8601 with offset (2026-10-20T09:00:00+03:00), or "best": Shager picks each account's next best time for its own market (get_best_times), at least 3 hours from its other posts, so a batch of posts spreads over the coming best hours. The answer's best_time shows what was picked.
workspace_idYesWorkspace id from list_workspaces
idempotency_keyNoAny unique string you choose (REST: the Idempotency-Key header works too). Retrying with the same key and body returns the first result instead of creating a second one. Kept 24 hours.
confirmation_tokenNoThe confirmation_token from needs_confirmation, after your human approved it at confirm_url. It works only once a person approved this exact plan in Shager.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / confirm / description
      Previous value: -"Deprecated boolean; does not bypass confirmation. A confirmation_token is required when a schedule goes to more than 10 accounts, starts within 60 minutes, or includes a Pinterest account. Without it you get needs_confirmation with the dispatch plan; show it to your human, then resend with confirmation_token from the returned plan."New value: +"Deprecated boolean; does not bypass confirmation. A confirmation_token is required when a schedule goes to more than 10 accounts, starts within 60 minutes, or includes a Pinterest account. Without it you get needs_confirmation with the dispatch plan and confirm_url, where your human approves it in Shager; then resend the same call."
    • changedInput schema / properties / confirmation_token / description
      Previous value: -"Token returned by needs_confirmation or validate_post for this exact plan; expires after 15 minutes."New value: +"The confirmation_token from needs_confirmation, after your human approved it at confirm_url. It works only once a person approved this exact plan in Shager."
  2. Changed5 schema fields changed
    • addedInput schema / properties / schedule_at / anyOf
      Added value: +[
      +  {
      +    "format": "date-time",
      +    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$",
      +    "type": "string"
      +  },
      +  {
      +    "const": "best",
      +    "type": "string"
      +  }
      +]
    • addedInput schema / properties / schedule_at / description
      Added value: +"ISO 8601 with offset (2026-10-20T09:00:00+03:00), or \"best\": Shager picks each account's next best time for its own market (get_best_times), at least 3 hours from its other posts, so a batch of posts spreads over the coming best hours. The answer's best_time shows what was picked."
    • removedInput schema / properties / schedule_at / format
      Removed value: -"date-time"
    • removedInput schema / properties / schedule_at / pattern
      Removed value: -"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z|([+-](?:[01]\\d|2[0-3]):[0-5]\\d)))$"
    • removedInput schema / properties / schedule_at / type
      Removed value: -"string"
  3. Changed1 schema field changed
    • changedInput schema / properties / confirm / description
      Previous value: -"Deprecated boolean; does not bypass confirmation. A confirmation_token is required when a schedule goes to more than 10 accounts or starts within 60 minutes. Without it you get needs_confirmation with the dispatch plan; show it to your human, then resend with confirmation_token from the returned plan."New value: +"Deprecated boolean; does not bypass confirmation. A confirmation_token is required when a schedule goes to more than 10 accounts, starts within 60 minutes, or includes a Pinterest account. Without it you get needs_confirmation with the dispatch plan; show it to your human, then resend with confirmation_token from the returned plan."
  4. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare destructiveHint and openWorldHint, but the description adds substantive context beyond them: full validation across all accounts, approval-state requirements, staggering logic (stagger_min/max_seconds plus per_channel.delay_minutes), and the failure path returning needs_confirmation with details.plan and confirm_url. It also discloses that publishing targets the person's real accounts, which is the key risk an agent must weigh.

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 with the core action and the safety warning, and every paragraph corresponds to a real decision the agent must make. It is dense — long compound sentences with parenthetical asides — and some detail (TikTok notes) could be trimmed, but little is genuinely wasted.

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 destructive, multi-step write with six parameters and no output schema, this covers what the agent needs: preconditions, validation behaviour, the confirmation loop and its plan payload, idempotency expectations, and the reschedule/cancel follow-ups. Nothing material to a correct invocation is left unstated.

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 83%, so the schema carries most of the load, yet the description still adds meaning: schedule_at is ISO 8601 with an offset and the workspace timezone governs display, and confirmation_token is only obtainable after a human approves the exact plan. It does not explain confirm or idempotency_key behaviour, both of which are documented in the schema instead.

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?

Opens with a specific verb-plus-resource framing: "Give an existing draft (or approved post) a time," which is precisely distinct from create_post. It names cancel_post as the counter-operation but never contrasts with create_post or update_post, so an agent must still infer that this tool is not the way to author or edit content.

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?

Explicitly gates usage: "only schedule when your human asked to publish it," names prerequisites (publish scope, claimed sandbox), and routes the move case to "call schedule_post again with the new time" while pointing cancellation at cancel_post. The confirmation threshold (>10 accounts, start within 60 minutes) is stated as a concrete when-condition rather than left implicit.

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