notebooklm-mcp-cli

Download All Artifacts

download_all_artifacts

Download all completed studio artifacts from one or all notebooks, saving each into a per-notebook folder. Skips unfinished or failed artifacts and reports them without stopping the rest.

Instructions

Download all completed studio artifacts of one notebook — or every notebook.

Creates a subdirectory of output_dir named after each notebook title and saves every completed artifact there, named after its title with the type's default extension (report → .md, mind_map → .json, video → .mp4, slide_deck → .pdf/.pptx, ...). Artifacts that are still generating or failed are skipped and listed in the result. A failure on one artifact (or one notebook in a sweep) does not stop the others.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`output_dir`	No	Base directory for the per-notebook folders, relative to the download directory (default: the download directory itself). Paths outside it are refused; see download_artifact.	.
`notebook_id`	No	Notebook UUID (omit when all_notebooks=True)
`all_notebooks`	No	Sweep every notebook in the account instead of one
`output_format`	No	For quiz/flashcards only: json\|markdown\|html	json
`skip_existing`	No	Skip artifacts whose target file already exists — makes repeated runs incremental
`artifact_types`	No	Restrict to these types, e.g. ["video", "slide_deck", "mind_map", "report"]. Default: all types.
`slide_deck_format`	No	For slide decks only: pdf (default) or pptx	pdf

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.11.5Sep 18, 2026

TDQS

A4.3/5.0

Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so admirably. It discloses directory creation, file naming and extension conventions, skipping of in-progress/failed artifacts, and partial-failure tolerance. These details go well beyond the structured schema.

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 compact and front-loaded, starting with the core behavior before covering exceptions and edge cases. Every sentence adds value, and the example extension list is efficiently embedded without bloating the prose.

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 seven params, no annotations, and rich behavior, the description covers the essential mechanics, edge cases, and failure semantics. The output schema exists, so not detailing the return value further is acceptable; the result is adequately characterized by the mention of skipped/failed artifacts being listed.

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%, so the schema already documents all seven parameters. The description adds context about extensions and per-notebook folders, but does not materially deepen understanding of individual parameters beyond what the schema provides. Baseline 3 is appropriate.

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, 'Download all completed studio artifacts of one notebook — or every notebook,' identifying both the resource and scope. It clearly distinguishes itself from the single-item sibling download_artifact by emphasizing bulk and sweep behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for downloading all artifacts or sweeping notebooks, but does not explicitly say when to prefer it over download_artifact or export_artifact. The output_dir parameter points to download_artifact for path restrictions, providing some cross-reference, but no direct when-to-use vs alternatives guidance is given.

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