notebooklm-mcp

Overview Schema Source Related Servers Discussions Admin

Notebook Query

notebook_query

Ask questions about content already in a NotebookLM notebook. Get AI answers grounded in your uploaded sources, without searching for new material.

Instructions

Ask AI about EXISTING sources already in notebook. NOT for finding new sources.

Use research_start instead for: deep research, web search, find new sources, Drive search.

Input Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	Question to ask
`timeout`	No	Wall-clock query budget in seconds (default: from env NOTEBOOKLM_QUERY_TIMEOUT or 120.0; source-heavy notebooks may need 180+)
`source_ids`	No	Source IDs to query (default: all)
`notebook_id`	Yes	Notebook UUID
`conversation_id`	No	For follow-up questions
`new_conversation`	No	Start a fresh conversation when conversation_id is omitted

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.11.2Sep 9, 2026
- addedInput schema / properties / conversation_id / description
```
Added value: +"For follow-up questions"
```
- addedInput schema / properties / new_conversation / description
```
Added value: +"Start a fresh conversation when conversation_id is omitted"
```
- addedInput schema / properties / notebook_id / description
```
Added value: +"Notebook UUID"
```
- addedInput schema / properties / query / description
```
Added value: +"Question to ask"
```
- addedInput schema / properties / source_ids / description
```
Added value: +"Source IDs to query (default: all)"
```
- addedInput schema / properties / timeout / description
```
Added value: +"Wall-clock query budget in seconds (default: from env NOTEBOOKLM_QUERY_TIMEOUT or 120.0; source-heavy notebooks may need 180+)"
```

Changed2 schema fields changedv0.9.12Aug 19, 2026

addedInput schema / properties / new_conversation

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

changedInput schema / properties / source_ids / anyOf

Previous value: -[
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

Addedv0.9.1Jul 22, 2026
Removedv0.8.9Jul 18, 2026
Changed5 schema fields changedv0.7.7Jun 20, 2026
- removedInput schema / properties / conversation_id / description
```
Removed value: -"For follow-up questions"
```
- removedInput schema / properties / notebook_id / description
```
Removed value: -"Notebook UUID"
```
- removedInput schema / properties / query / description
```
Removed value: -"Question to ask"
```
- removedInput schema / properties / source_ids / description
```
Removed value: -"Source IDs to query (default: all)"
```
- removedInput schema / properties / timeout / description
```
Removed value: -"Request timeout in seconds (default: from env NOTEBOOKLM_QUERY_TIMEOUT or 120.0)"
```
First observedv0.6.13May 31, 2026

TDQS

A4.2/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It does clarify an important scope constraint: the tool only queries existing notebook sources and is not for discovery. However, it does not state whether the query is read-only, whether it creates conversation state, whether it has significant cost/latency, or any auth prerequisites. Some of this is implied but not explicit.

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 two short sentences with no filler. The core scoping is front-loaded, and the exclusion/alternative is immediately actionable. Every phrase earns its place.

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?

Given the rich input schema and presence of an output schema, the description covers the most important usage context: existing sources only and the main alternative for discovery. It does not address related siblings like notebook_query_start or cross_notebook_query, nor does it cover behavioral caveats such as cost or side effects, so it is strong but not fully comprehensive.

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 description coverage is 100%, and the schema itself gives detailed, meaningful parameter descriptions including defaults, timeout behavior, source filtering, and conversation IDs. The description adds only high-level context about querying existing sources and does not need to repeat parameter details, so it stays at the baseline.

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 states a specific action and resource: 'Ask AI about EXISTING sources already in notebook.' It also explicitly draws the boundary against finding new sources, which immediately distinguishes it from sibling tools like research_start. This is a clear, non-tautological purpose statement.

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?

It gives an explicit routing rule: 'Use research_start instead for: deep research, web search, find new sources, Drive search.' This directly tells the agent when not to use this tool and which alternative to pick, leaving little to inference.

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