Skip to main content
Glama

Set or clear the TikTok choice of a post

clipember_set_tiktok_choice
Idempotent

Set the TikTok choice of ONE TikTok post that hasn't gone out (draft or queued) — for example one that waits in the TikTok queue — or clear it with tiktokOptions=null so it waits for the user there again. The choice's caption replaces the post's caption. TikTok choice (tiktokOptions): send it only when the user has told you, for THIS post, who can see it, whether comments, duets and stitches are allowed, and whether it promotes their own brand or is a paid partnership. You must pass privacyLevel explicitly — there is no default — and every other field too; nothing is filled in for you, and never copy a choice from another post, account or template. The server checks it against that TikTok account's current settings (audiences it offers, interactions the creator turned off, longest video it accepts) and refuses a choice that doesn't fit. With a choice the post goes straight to the profile at the scheduled time; by sending it you confirm the user agrees to TikTok's Music Usage Confirmation (and Branded Content Policy for a paid partnership). Without one the post waits in the TikTok queue (https://clipember.com/tiktok-queue) for the user to choose; if nobody does before the scheduled time, TikTok receives it as a draft in the user's TikTok Inbox to finish in the TikTok app.

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>",
      "tiktokOptions": "<tiktokOptions>"
    },
    "name": "clipember_set_tiktok_choice"
  }
}

Input Schema

NameRequiredDescriptionDefault
postIdYesA TikTok post id (clipember_list_scheduled_posts)
tiktokOptionsYesThe full choice for this post (every field required), or null to clear it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly=false, openWorld=true, idempotent=true, destructive=false), the description discloses server-side validation against the TikTok account's live settings and that invalid choices are refused, plus a legal consent consequence (Music Usage Confirmation / Branded Content Policy). It also explains the downstream branching: straight to profile, waits in the queue, or lands as a draft in the user's TikTok Inbox.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite its length it is front-loaded with the action, then preconditions, then validation/consent, then outcomes — a logical progression with no filler sentences. The em-dash clauses are dense but each one carries a distinct constraint or consequence.

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 two-parameter write tool with no output schema, the description covers everything an agent needs: required-per-post user input, refusal behavior, consent implications, and what happens at scheduled time with and without a choice. Nothing material is left to inference.

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 schema already carries the field-level semantics and the baseline is 3. The description still adds operational meaning: privacyLevel has no default and must be passed explicitly, every field is mandatory with nothing filled in, and the choice must be sourced from the user for this specific post rather than reused — guidance the schema does not encode.

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?

The description opens with a concrete verb and resource — 'Set the TikTok choice of ONE TikTok post that hasn't gone out (draft or queued)' — and adds the inverse operation ('clear it with tiktokOptions=null'). It is unambiguous about what the call does, though it never names a sibling (e.g. clipember_get_tiktok_creator_info) to draw the read-vs-write boundary explicitly.

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 states a per-post precondition ('send it only when the user has told you, for THIS post, who can see it, whether comments, duets and stitches are allowed, and whether it promotes their own brand or is a paid partnership') and the negative path (omit the choice and the post waits in the queue; null clears it). Explicit anti-patterns — 'never copy a choice from another post, account or template' — are exactly the kind of exclusion guidance an agent needs.

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