NotebookLM MCP Server

Overview Schema Source Related Servers Discussions Admin

Chat Ask

chat_ask

Ask a notebook's sources questions to get grounded answers with citations, continue a conversation, or recall prior Q&A pairs. Scope queries to specific sources as needed.

Instructions

Ask a notebook's sources a question, and/or recall prior turns. Accepts a notebook name or ID.

Pass conversation_id to continue a specific conversation; omit it to continue the notebook's most-recent conversation (or start a new one).

source_ids (optional) scopes the question to specific sources by id/prefix/title; omit it to query every source. It accepts a real list, a JSON-array string, or a comma-separated string (the comma form cannot carry a source title that itself contains a comma — use a JSON array or a real list for those).

history (optional, default 0): the max number of prior Q&A pairs (each a {question, answer}) to also return (oldest-first), from the conversation as it stood before this question. There is no unbounded "all" value — pass a generously large number (e.g. 100) for the whole conversation. Omit question (leave it empty) with history > 0 to recall prior pairs without asking anything new; a recall-only call also echoes the conversation_id it read. Pass neither and the call is rejected.

Returns the answer, turn_number, and citation references (when a question is asked). references controls citation detail: lite (default) returns source_id / citation_number / cited_text; full adds chunk-level char offsets and scores.

suggest_followups (optional, default False): when True the result also carries a suggested_prompts list of AI-suggested follow-up questions (each a {title, prompt}), scoped to the same source_ids and steered by question when one is given. It works on its own too — pass it with no question (and history 0) to get suggested questions without asking anything. When omitted/False the result never contains a suggested_prompts key.

Input Schema

TableJSON Schema

Name	Required	Default
`history`	No
`notebook`	Yes
`question`	No
`references`	No	lite
`source_ids`	No
`conversation_id`	No
`suggest_followups`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 15, 2026

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: it explains conversation continuation behavior, the rejection when neither question nor history is passed, the recall-only echo of conversation_id, the lack of an unbounded 'all' value for history, the structure of returned references (lite vs full), and the conditional presence of suggested_prompts. This is rich, transparent behavioral disclosure that goes well beyond what the schema provides.

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 long but front-loaded with the core purpose, then organized into focused paragraphs per parameter and behavior. Every sentence earns its place by explaining a distinct rule or edge case (e.g., the comma-separated source_ids caveat, the recall-only echo, the rejection condition). There is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (7 parameters, no annotations, an output schema that exists but is not shown here), the description is complete enough for an agent to invoke the tool correctly. It covers all inputs, defaults, edge cases, return shape details, and the interaction between question, history, and suggest_followups. Nothing essential is missing.

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 must compensate and it does. Every parameter is documented in prose: notebook (name or ID), question (omitted for recall-only), conversation_id (continue a specific conversation), source_ids (scoping, accepted formats including the comma limitation), history (default 0, max prior Q&A pairs, no unbounded value), references (lite/full detail), and suggest_followups (default False, works alone). This fully covers the 7 parameters and adds meaning beyond the bare schema types.

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: 'Ask a notebook's sources a question, and/or recall prior turns.' It clearly distinguishes this tool from siblings like chat_start, chat_status, and suggest_prompts by focusing on question-answering and recall, and it names the required input (notebook name or ID). An agent can tell what the tool does without opening the schema.

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 context for when to use the tool (ask a question, recall history, or get suggested follow-ups) and explains key decision points such as passing conversation_id vs omitting it, and using history > 0 with an empty question for recall-only. However, it never explicitly names alternative tools like suggest_prompts or chat_start, so it lacks direct 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.