Send to a Topic
send_to_topicSave the title, summary, and links the user explicitly asks to send to Carl or CarlNotes, with phrases like send this to Carl, save this to CarlNotes, add this to my topic, share this with Carl, or forward this to Carl. A good send summarizes what the user is working on or asking about, what they concluded, open questions, and the links that mattered. Never paste the raw conversation. Include chat_url only when a real conversation URL is available from the host or user. Codex can use codex://threads/ when its real local thread ID is known. Never invent an ID or publish a conversation to obtain a URL. Supply topic_ids with one to twenty distinct Topics the user can edit (topic_id remains accepted for one), including editable public, private, invite, and Team Topics. When the user asks to send but names no Topic, first call suggest_topics and wait for their choice. Never send on your own initiative. A successful call atomically stores a sender-private entry in every selected Topic and counts once toward the daily send limit. If any destination is rejected, nothing is stored or charged. Reuse request_id for a retry of exactly the same content and destinations. Its text and links inform each Topic's scoring. Findings have page-only public explanations and sender-only annotations; podcasts narrate only the public explanation. On a Topic-bound connection every supplied ID must match the bound Topic; use /mcp for another Topic. An active connected CarlNotes account is required.
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": {
"title": "<title>",
"summary": "<summary>"
},
"name": "send_to_topic"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| links | No | ||
| title | Yes | ||
| summary | Yes | ||
| chat_url | No | ||
| topic_id | No | ||
| topic_ids | No | ||
| request_id | No |