notebooklm-mcp

by gracelee087

Overview Schema Source Related Servers Discussions Admin

Python

Local

research_start

Start a fast research session on any topic, returning suggested sources for import into an empty NotebookLM notebook.

Instructions

Kick off NotebookLM's Discover (Fast Research) flow on a topic.

Returns { query, sources: [{ url, title, description }, ...] }.

The candidate sources are NOT automatically added to the notebook. Use source_add(kind="url", value=<chosen_url>) to import selected ones.

Requires an EMPTY notebook — NotebookLM disables Discover once the notebook has content. Create one with notebook_create first if needed.

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": {
      "notebook_id": "<notebook_id>",
      "query": "<query>"
    },
    "name": "research_start"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes
`notebook_id`	Yes
`timeout_sec`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Aug 2, 2026

TDQS

A4.4/5.0

Behavior5/5

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It explicitly states that candidate sources are NOT automatically added, that the notebook must be empty, and it specifies the return shape. These are non-obvious, important behaviors that materially affect invocation and follow-up actions.

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?

The description is four sentences, front-loaded with the main purpose, then the return format, then crucial caveats. Every sentence carries meaningful information without repetition or filler.

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?

The description provides enough context to invoke the tool correctly: purpose, output format, prerequisite, and next-step action. It lacks a comparison to research_and_ask and does not describe error behavior or timeout handling, but for a non-destructive research starter with a simple output shape, it is largely complete.

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?

The schema has 0% description coverage, so the description must compensate. It clarifies that query is the topic and that notebook_id must refer to an empty notebook, but it never explains timeout_sec or its default behavior. This is partial compensation at best, leaving one parameter semantically undocumented.

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 uses a specific verb+resource: 'Kick off NotebookLM's Discover (Fast Research) flow on a topic.' It clearly states the tool starts a research discovery process and returns candidate sources, which distinguishes it from notebook querying or source management tools like research_and_ask or source_add.

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?

The description gives clear usage context: it requires an empty notebook, advises creating one with notebook_create if needed, and directs the agent to use source_add to import selected sources. However, it does not explicitly compare this to research_and_ask or other research-related tools, so it stops short of full when-to-use vs. alternatives guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.