Skip to main content
Glama

x_publish

Post to the user's connected X account: text alone, or with 1 to 4 project images (imageAssetIds) or one finished export (exportTaskId), only when the user asked to post. Text: the user's words; with none, write a short draft and ask, never a project or file name.

Actions:

  • prepare: returns a draft; confirm it with the user in your own interface as the widget-forms Skill's X post section says for your host, then end your turn. Nothing is posted until they confirm. In the same reply, state the credits from the result, and say plainly when a link makes X charge far more. An ignored draft stays in memory until submitted, cancelled, replaced or the page reloads; prepare again replaces it, no cancel needed.

  • publish: only after the user confirmed. Pass approvalId and text, the exact final text they confirmed. Returns the postUrl or a pending state.

  • publish with direct=true and no approvalId: posts at once, only when the user's own message says to post without confirming ("post it directly", "直接发", "不用确认", "批量发") and gives the complete post (text, and media if any); otherwise prepare. One call per post; after each, tell them the account, text, media, credits and postUrl. A draft you asked them to confirm waits for that confirmation.

  • status: checks the original approvalId or publicationRequestId with the same accountTarget and reports what X confirms. For a media post, include postId if known to check it against the original upload.

  • retry: when the user wants to retry, pass the original ID. ChatCut checks the original attempt before starting a linked retry. An unknown result can still produce a duplicate.

  • cancel: withdraws a draft or stops work that can still be stopped. If X may have accepted it, check its status.

Use prepare for another post at any time. Reply with the confirmed postUrl as a Markdown link. Keep the project's editor tab open. Not connected or expired: manage_connectors action=connect. Insufficient credits: report it, do not retry.

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": {
      "action": "<action>"
    },
    "name": "x_publish"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoThe post text. Use the user's words. If they gave none, draft text for this content and ask them; never use the project, timeline or file name. The user can edit it before posting. With publish: omit it in ChatCut's own chat (the submitted form decides); elsewhere pass the exact final text the user confirmed. With direct: the user's complete text. If X rejects the post text, report its reason and get approval for any edits before submitting another post.
actionYesprepare, publish, status, retry or cancel. publish only after the user confirmed the draft (in ChatCut's own chat by submitting its form, elsewhere in your own interface), or with direct=true when they explicitly asked to post without confirming.
directNotrue with action=publish and no approvalId: post now without a draft to confirm, only when the user explicitly asked to post without confirming and gave the complete post.
postIdNoA known numeric X post ID to check against an original media upload.
projectIdNoProject for this call (full ID or unambiguous prefix). Explicit-timeline calls never change the target of later calls; legacy project selection applies otherwise.
approvalIdNoReturned by prepare. Pass it back unchanged for publish, status, retry or cancel of the same draft or post.
timelineIdNo
exportTaskIdNoFor a video post: the finished MP4 export (renderId from submit_export on the Web, taskId from export on Desktop).
accountTargetNoExact account {accountId, revision} from list_connectors. Required on every platform call.
imageAssetIdsNo1 to 4 image asset IDs from this project (JPEG, PNG or WebP up to 5 MiB, GIF up to 15 MiB) to attach instead of a video. Omit both this and exportTaskId for a text-only post.
publicationRequestIdNoReturned once the post is submitted. Pass it back unchanged with status, retry or cancel.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"prepare, publish, status or cancel. publish only after the user confirmed the draft (in ChatCut's own chat by submitting its form, elsewhere in your own interface), or with direct=true when they explicitly asked to post without confirming."New value: +"prepare, publish, status, retry or cancel. publish only after the user confirmed the draft (in ChatCut's own chat by submitting its form, elsewhere in your own interface), or with direct=true when they explicitly asked to post without confirming."
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "prepare",
      -  "publish",
      -  "status",
      -  "cancel"
      -]New value: +[
      +  "prepare",
      +  "publish",
      +  "status",
      +  "cancel",
      +  "retry"
      +]
    • changedInput schema / properties / approvalId / description
      Previous value: -"Returned by prepare. Pass it back unchanged for publish, status or cancel of the same draft or post."New value: +"Returned by prepare. Pass it back unchanged for publish, status, retry or cancel of the same draft or post."
    • addedInput schema / properties / postId
      Added value: +{
      +  "description": "A known numeric X post ID to check against an original media upload.",
      +  "pattern": "^\\d{1,19}$",
      +  "type": "string"
      +}
    • changedInput schema / properties / publicationRequestId / description
      Previous value: -"Returned once the post is submitted. Pass it back unchanged with status."New value: +"Returned once the post is submitted. Pass it back unchanged with status, retry or cancel."
    • changedInput schema / properties / text / description
      Previous value: -"The post text, up to 280 characters (a link counts 23, a CJK character 2). Use the user's words. If they gave none, write a short draft for this content and ask them; never use the project, timeline or file name. The user can still edit it before posting. With publish: omit it in ChatCut's own chat (the submitted form decides); elsewhere pass the exact final text the user confirmed. With direct: the user's complete text."New value: +"The post text. Use the user's words. If they gave none, draft text for this content and ask them; never use the project, timeline or file name. The user can edit it before posting. With publish: omit it in ChatCut's own chat (the submitted form decides); elsewhere pass the exact final text the user confirmed. With direct: the user's complete text. If X rejects the post text, report its reason and get approval for any edits before submitting another post."
    • removedInput schema / properties / text / maxLength
      Removed value: -280
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive, so the bar is lower, and the description still adds real context: draft lifetime ('stays in memory until submitted, cancelled, replaced or the page reloads'), duplicate risk on retry, credit charging and the X link surcharge, and the pending-state return. Minor gap: it does not say what a 'pending state' response contains for the agent to act on.

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 is front-loaded in one sentence, then the five actions are bulleted for scannability, which suits an 11-parameter, multi-mode tool. It is dense and slightly overgrown in places (the draft-lifetime aside, the 'Markdown link' and 'keep the editor tab open' instructions), but nearly every line carries operational weight.

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 complex open-world write tool with 11 parameters, a nested accountTarget, and no output schema, the description covers the full lifecycle: draft, confirm, post, check, retry, cancel, plus auth and credit failure paths. It even states the return values ('postUrl or a pending state'), which the missing output schema would otherwise leave unknown.

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 91%, so the schema already documents most parameters, yet the description still adds workflow meaning the schema cannot: approvalId chaining from prepare to publish/status/retry/cancel, direct=true as the escape hatch from the approval loop, and imageAssetIds versus exportTaskId as mutually exclusive media paths.

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 sentence names a specific verb and resource: post to the user's connected X account, with the three media shapes spelled out (text only, 1-4 imageAssetIds, or one exportTaskId) and an explicit gate ('only when the user asked to post'). This distinguishes it cleanly from siblings like x_delete_post, x_get_statistics, and manage_connectors.

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?

The Actions list gives when-to-use for every mode: prepare for drafting, publish only after confirmation, direct=true only when the user's own message says to skip confirmation (with concrete trigger phrases), status to reconcile an unknown result, retry for re-attempts, cancel to withdraw. It also routes to an alternative when unconnected ('manage_connectors action=connect') and forbids retry on insufficient credits.

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.