Skip to main content
Glama

CarlNotes

Send to a Topic

send_to_topic

Save 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

NameRequiredDescriptionDefault
linksNo
titleYes
summaryYes
chat_urlNo
topic_idNo
topic_idsNo
request_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is partly covered. The description adds substantial context the annotations lack: atomic storage across all destinations, one unit of the daily send limit, all-or-nothing rejection with no charge, request_id reuse for retries, page-only public explanations, and the requirement of an active connected account. It stops short of describing the success response or how to interpret a partial rejection payload.

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?

Content is front-loaded: the trigger condition comes first, then content guidance, then destination rules, then failure/retry semantics. It is dense and mostly earns its length, but a few clauses are stacked into single run-on sentences and the findings/podcast disclosure sentence sits awkwardly among the call mechanics.

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 seven-parameter, no-output-schema write tool, the description covers triggers, content shape, destination selection, atomicity, retry, and auth prerequisites. The remaining gap is the return behavior: with no output schema and no statement of what a successful call returns, an agent cannot describe the result to the user beyond 'it was stored'.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden, and it does: title/summary as a synthesized conclusion, links as the links that mattered, chat_url restricted to real host/user URLs with the codex://threads/<verified-thread-id> form, topic_ids limited to one to twenty distinct editable Topics with topic_id still accepted for one, and request_id semantics for retry. Only the array caps (10 links) and string length bounds are left entirely to the schema.

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 description opens with a specific verb-and-resource pair: it saves a title, summary, and links into one or more CarlNotes Topics at the user's explicit request. It also lists the exact trigger phrases ('send this to Carl', 'add this to my topic') that distinguish this tool from adjacent write tools such as create_topic or post_to_team_room.

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?

Usage rules are explicit and actionable: never send on your own initiative, call suggest_topics and wait when the user names no Topic, include chat_url only when a real URL exists, never invent an ID. It also states the Topic-bound connection constraint and points to /mcp as the alternative for another Topic, which is a genuine when-not condition.

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.