Skip to main content
Glama

Edit a post that hasn't gone out

clipember_update_post
Idempotent

Change ONE post — one account of a post group (postId from clipember_list_scheduled_posts or clipember_create_post) — while it is a draft or queued: its caption, network settings (YouTube title or privacy, LinkedIn visibility, …), time, draft ↔ queued (status "queued" puts a draft into the queue at scheduledFor, or at its current time; "draft" takes it out of the queue), or another account of the same network (connectionId). A failed post accepts only caption and settings — retry it with clipember_retry_failed_post. Send only what changes; the settings you pass are merged into the post's current ones. The video of a post can't be changed. TikTok: the TikTok choice isn't set here — use clipember_set_tiktok_choice, only with the user's explicit answer for this post. A new caption on a TikTok post that has a choice becomes the choice's caption too; moving a TikTok post to another account drops its choice (it was made for the other account). Approvals: with client approval ("Publish only approved") or team approval on, queuing may keep the post a draft — the result says so — and changing the caption, settings or account of an approved post can make it need approval again (a team member under team approval: of any queued post — it becomes a draft until the owner or an admin approves). Queuing a YouTube, Instagram or other post publishes it publicly at its time — confirm with the user first.

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": {
      "postId": "<postId>"
    },
    "name": "clipember_update_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
postIdYesThe post id — one account of a post group
statusNoqueued = put a draft into the queue; draft = take a queued post out of the queue
captionNoNew text exactly as it should appear; null clears it (a clip then gets its AI caption when it posts). Limits: TikTok 2200, YouTube description 5000, Instagram 2200, LinkedIn 3000, Bluesky 300.
settingsNoNetwork options to change, merged into the current ones (e.g. {title} renames a YouTube Short and keeps its privacy). Not for TikTok (clipember_set_tiktok_choice).
connectionIdNoMove the post to another account of the same network (id from clipember_list_platform_connections)
scheduledForNoNew time, ISO 8601, e.g. 2026-12-01T15:00:00Z

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / caption / description
      Previous value: -"New text exactly as it should appear; null clears it (a clip then gets its AI caption when it posts). Limits: TikTok 2200, YouTube description 5000, Instagram 2200."New value: +"New text exactly as it should appear; null clears it (a clip then gets its AI caption when it posts). Limits: TikTok 2200, YouTube description 5000, Instagram 2200, LinkedIn 3000, Bluesky 300."
    • changedInput schema / properties / settings / description
      Previous value: -"Network options to change, merged into the current ones (e.g. {title} renames a YouTube Short and keeps its privacy). Not for TikTok (clipember_set_tiktok_choice) or Threads."New value: +"Network options to change, merged into the current ones (e.g. {title} renames a YouTube Short and keeps its privacy). Not for TikTok (clipember_set_tiktok_choice)."
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

With annotations already declaring non-readOnly, idempotent, non-destructive, the description goes well beyond them: merge-not-replace semantics, the video being immutable, a new TikTok caption propagating to the choice, moving a TikTok post dropping its choice, approval being invalidated by edits, and the queue-publishes-publicly side effect. These are exactly the hidden consequences an agent would otherwise get wrong.

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 action and scope in the first clause, then layered with exceptions. Every sentence carries a distinct rule, but the single dense paragraph and parenthetical asides make it harder to scan than an ordered list of constraints would be.

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 a nested settings object and no output schema, the description covers the mutation surface, merge semantics, immutability constraints, cross-tool routing, and approval/publication side effects that the return value implies ('the result says so'). Nothing an agent needs to call it safely is missing.

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 still adds real meaning: 'send only what changes' plus merge behavior for `settings`, the two-way semantics of `status` (queued places at scheduledFor or current time), and `connectionId` being constrained to the same network. It stops short of restating per-field limits, which the schema already covers.

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 (change) and resource (one post / one account of a post group) and enumerates the mutable fields — caption, network settings, time, draft↔queued status, connection. It explicitly separates itself from clipember_create_post, clipember_retry_failed_post and clipember_set_tiktok_choice, so an agent can route correctly without opening schemas.

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 hard preconditions (only while draft or queued) and explicit alternatives with their trigger conditions: failed posts go to clipember_retry_failed_post, TikTok choice goes to clipember_set_tiktok_choice and only with explicit user answer. It also adds a confirmation requirement before queueing anything that publishes publicly.

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