Skip to main content
Glama

vault.batch

Run multiple questions against a NotebookLM notebook and save each answer as markdown and JSON files with cited sources for building a searchable vault.

Instructions

Run a list of questions against a notebook and persist each answer to disk as two artifacts: {slug}.md (markdown with YAML frontmatter, answer body and cited source excerpts) and {slug}.json (structured payload conforming to the nblm-answer-v1 schema). Designed for one-shot ingestion of a notebook into a searchable markdown vault (e.g. for indexing with RTFM) — every answer keeps titles + highlighted excerpts, so repeat queries no longer need to round-trip through NotebookLM.

Reuses the same browser/session as ask_question — no HTTP server required. Pass sleep_between_ms (1500–3000ms) for batches above ~20 questions to avoid hammering NotebookLM.

Returns per-question file paths, success flags, citation counts and the resolved session id. See the RTFM integration guide for the recommended workflow.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
questionsYesNon-empty array of question strings to ask sequentially.
vault_dirYesDestination directory (absolute or relative). Created with mkdir -p if missing.
notebook_idNoOptional library notebook id to query. Falls back to the active notebook.
notebook_urlNoOptional NotebookLM URL (overrides notebook_id). Use for ad-hoc notebooks.
slug_prefixNoOptional filename prefix (e.g. "sota", "market-2026q2"). Default: "".
source_formatNoCitation extraction mode. "json" (default) preserves titles + excerpts in the sidecar.
sleep_between_msNoPause between questions in ms. 1500–3000 is sane for batches above ~20.
session_idNoOptional session id to reuse for context continuity across the batch.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
successYesWhether the tool call succeeded.
dataNoThe tool payload on success. The exact shape depends on the tool.
errorNoHuman-readable error message, present only when success is false.
Behavior4/5

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

Annotations indicate readOnlyHint=false (mutates), idempotentHint=false, openWorldHint=true. The description adds context: persists to disk, reuses browser/session, no HTTP server needed. No contradictions; it explains what artifacts are created.

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 concise, with 5 sentences that front-load the core action and provide necessary details without extraneous information.

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 8 parameters and an output schema, the description explains return values (file paths, success flags, etc.) and references an integration guide, covering key aspects for a complete understanding.

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?

Input schema has 100% coverage with good descriptions. The description adds marginal extra value by suggesting sleep_between_ms range and explaining source_format modes, but does not significantly enhance understanding beyond 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 clearly states the tool runs a list of questions against a notebook and persists answers to disk as markdown and JSON artifacts. It distinguishes itself from sibling tools like notebook.ask by emphasizing batch processing and one-shot ingestion.

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 provides context for when to use: 'Designed for one-shot ingestion' and 'reuses the same browser/session as ask_question.' It also gives guidance on sleep_between_ms for large batches. However, it does not explicitly mention when not to use or compare to alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/roomi-fields/notebooklm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server