Skip to main content
Glama

Approve or reject an Autopilot proposal

clipember_decide_autopilot_proposal

Approve or reject a pending Autopilot post proposal (from clipember_list_autopilot_proposals). Approving WILL schedule the post to publish publicly — optionally edit the caption or add/change platforms first. Rejecting removes it from the queue; a reason helps Autopilot's learning loop.

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": {
      "proposalId": "<proposalId>",
      "action": "<action>"
    },
    "name": "clipember_decide_autopilot_proposal"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
reasonNoWhy rejected — feeds Autopilot's learning loop
captionNoOverride the AI-generated caption before approving
platformsNoPublish to these platforms instead of just the one proposed. LinkedIn needs its visibility chosen in the automation settings; Bluesky needs a caption of 300 characters or less.
proposalIdYes
reasonNoteNo
scheduledForNoOverride the proposed publish time

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / platforms / items / enum
      Previous value: -[
      -  "tiktok",
      -  "youtube_shorts",
      -  "instagram_reels",
      -  "bluesky",
      -  "facebook_reels",
      -  "threads",
      -  "linkedin"
      -]New value: +[
      +  "tiktok",
      +  "youtube_shorts",
      +  "instagram_reels",
      +  "bluesky",
      +  "facebook_reels",
      +  "threads",
      +  "linkedin",
      +  "pinterest"
      +]
    • changedInput schema / properties / platforms / maxItems
      Previous value: -7New value: +8
  2. Changed1 schema field changed
    • changedInput schema / properties / platforms / description
      Previous value: -"Publish to these platforms instead of just the one proposed. LinkedIn needs its visibility chosen in the automation settings; Bluesky (300) and Threads (500) need a short caption."New value: +"Publish to these platforms instead of just the one proposed. LinkedIn needs its visibility chosen in the automation settings; Bluesky needs a caption of 300 characters or less."
  3. Changed3 schema fields changed
    • changedInput schema / properties / platforms / description
      Previous value: -"Publish to these platforms instead of just the one proposed"New value: +"Publish to these platforms instead of just the one proposed. LinkedIn needs its visibility chosen in the automation settings; Bluesky (300) and Threads (500) need a short caption."
    • changedInput schema / properties / platforms / items / enum
      Previous value: -[
      -  "tiktok",
      -  "youtube_shorts",
      -  "instagram_reels"
      -]New value: +[
      +  "tiktok",
      +  "youtube_shorts",
      +  "instagram_reels",
      +  "bluesky",
      +  "facebook_reels",
      +  "threads",
      +  "linkedin"
      +]
    • changedInput schema / properties / platforms / maxItems
      Previous value: -3New value: +7
  4. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false; the description adds the crucial consequence that approving 'WILL schedule the post to publish publicly' and that rejecting deletes it from the queue — real side-effect disclosure beyond the annotation flags. Idempotency and whether an approval can be undone are not addressed, keeping it below 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.

Conciseness5/5

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

Three sentences, each carrying a distinct payload: identity/source, approve-side consequence and options, reject-side consequence. The consequential warning is front-loaded with emphasis and no filler wording appears.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter mutation tool with a nested caption object and no output schema, the definition covers the decision branches and the highest-risk outcome (public publishing). Minor omissions remain: no mention of the scheduledFor override in prose and no hint of what the tool returns, though the schema carries those details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at 57%, the schema already documents reason, caption, platforms (including the LinkedIn/Bluesky constraints) and scheduledFor. The description adds only the sequencing hint that caption and platform edits happen before approval; it never mentions scheduledFor or reasonNote, so the gap is not fully compensated.

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 pair plus the resource: 'Approve or reject a pending Autopilot post proposal', and names the sibling that produces those proposals (clipember_list_autopilot_proposals). An agent can distinguish this from clipember_decide_team_approval and from the create/schedule tools without inspecting 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operative context for both branches: approving comes with the prerequisite option to edit caption/platforms first, and rejecting is described as removing from the queue. It does not explicitly state when this tool is the wrong choice (e.g. versus a team approval decision), so it stops short of full alternative routing.

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