Skip to main content
Glama

CarlNotes

Brew a topic

start_scan

Start a brew of a CarlNotes topic now. Carl reads its sources and keeps what's worth reading, and the brew sends its report and records its podcast episode like any other. It takes one of the account's daily brews, and only the topic's owner or an admin may start it. Past the daily limit no brew starts and nothing bills. Use it when the user asks Carl or CarlNotes to run a topic, with phrases like brew this topic now or run this topic now.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
topic_idNoThe topic's id. Optional on a topic-bound server, which already knows its topic.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), it discloses the quota model (one of the account's daily brews), the failure mode past the limit (no brew starts and nothing bills), the permission requirement, and the downstream effects of sending a report and recording a podcast episode. That is exactly the context an agent needs before triggering a billable side effect.

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?

Three sentences, front-loaded with the action and followed by behavior and constraints, with no wasted preamble. Minor filler exists — "like any other" and "keeps what's worth reading" are slightly loose phrasing — but nothing obscures the core instruction.

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?

With no output schema, the description covers outcomes well (report sent, podcast recorded, nothing happens past the quota). It does not say what the call returns or that progress should be checked via read_scan_status, which is the one thing an agent still has to infer.

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?

Schema coverage is 100% and the single topic_id parameter is fully documented in the schema, including its optionality on a topic-bound server. The description adds no further parameter meaning, which is acceptable here because the schema carries the burden.

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?

"Start a brew of a CarlNotes topic now" names a specific verb and resource, and the description clarifies what a brew does (reads sources, sends a report, records a podcast episode). It never names a sibling such as read_scan_status or stop_scan, so the distinction from them is only implied by the word "start" and the emphasis on "now".

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?

It gives concrete invocation triggers — "when the user asks Carl or CarlNotes to run a topic" with example phrases like "brew this topic now" — and states the precondition that only the owner or an admin may start it. It stops short of explicitly naming alternatives or restating which sibling to use when the user just wants status or to cancel.

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.