Skip to main content
Glama
jacob-bd

notebooklm-mcp

by jacob-bd
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Download Artifact

download_artifact

Save NotebookLM artifacts like audio, video, reports, mind maps, and slide decks to a local file by specifying the notebook and artifact type.

Instructions

Download any NotebookLM artifact to a file.

Unified download tool replacing 9 separate download tools. Supports all artifact types: audio, video, report, mind_map, slide_deck, infographic, data_table, file, quiz, flashcards.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
waitNoPoll while the artifact download is still propagating
artifact_idNoOptional specific artifact ID (uses latest if not provided)
notebook_idYesNotebook UUID
output_pathYesWhere to save the file, relative to the download directory (e.g. "podcast.m4a" or "My Notebook/report.md"). Downloads are confined to that directory; a path outside it is refused. It defaults to ~/Downloads/gemini-notebook and the operator can move it with NOTEBOOKLM_DOWNLOAD_DIR. The saved absolute path comes back in the result.
wait_timeoutNoService polling budget when ``wait`` is enabled; internal CDN retries and the file transfer can extend total wall time
artifact_typeYesType of artifact to download: - audio: Audio Overview (MP4/MP3) - video: Video Overview (MP4) - report: Report (Markdown) - mind_map: Mind Map (JSON) - slide_deck: Slide Deck (PDF or PPTX) - infographic: Infographic (PNG) - data_table: Data Table (CSV) - data_table_xlsx: Data Table Excel export (XLSX) - file: Generic Studio file export - quiz: Quiz (json|markdown|html) - flashcards: Flashcards (json|markdown|html)
output_formatNoFor quiz/flashcards only: json|markdown|html (default: json)json
poll_intervalNoSeconds between readiness checks
slide_deck_formatNoFor slide_deck only: pdf (default) or pptxpdf

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.13.0
    • changedInput schema / properties / wait_timeout / description
      Previous value: -"Maximum seconds to wait when ``wait`` is enabled"New value: +"Service polling budget when ``wait`` is enabled; internal\nCDN retries and the file transfer can extend total wall time"
  2. Changed9 schema fields changedv0.11.2
    • addedInput schema / properties / artifact_id / description
      Added value: +"Optional specific artifact ID (uses latest if not provided)"
    • addedInput schema / properties / artifact_type / description
      Added value: +"Type of artifact to download:\n- audio: Audio Overview (MP4/MP3)\n- video: Video Overview (MP4)\n- report: Report (Markdown)\n- mind_map: Mind Map (JSON)\n- slide_deck: Slide Deck (PDF or PPTX)\n- infographic: Infographic (PNG)\n- data_table: Data Table (CSV)\n- data_table_xlsx: Data Table Excel export (XLSX)\n- file: Generic Studio file export\n- quiz: Quiz (json|markdown|html)\n- flashcards: Flashcards (json|markdown|html)"
    • addedInput schema / properties / notebook_id / description
      Added value: +"Notebook UUID"
    • addedInput schema / properties / output_format / description
      Added value: +"For quiz/flashcards only: json|markdown|html (default: json)"
    • addedInput schema / properties / output_path / description
      Added value: +"Where to save the file, relative to the download\ndirectory (e.g. \"podcast.m4a\" or \"My Notebook/report.md\").\nDownloads are confined to that directory; a path outside it is\nrefused. It defaults to ~/Downloads/gemini-notebook and the\noperator can move it with NOTEBOOKLM_DOWNLOAD_DIR. The saved\nabsolute path comes back in the result."
    • addedInput schema / properties / poll_interval / description
      Added value: +"Seconds between readiness checks"
    • addedInput schema / properties / slide_deck_format / description
      Added value: +"For slide_deck only: pdf (default) or pptx"
    • addedInput schema / properties / wait / description
      Added value: +"Poll while the artifact download is still propagating"
    • addedInput schema / properties / wait_timeout / description
      Added value: +"Maximum seconds to wait when ``wait`` is enabled"
  3. Changed3 schema fields changedv0.9.7
    • addedInput schema / properties / poll_interval
      Added value: +{
+  "default": 5,
+  "type": "number"
+}
    • addedInput schema / properties / wait
      Added value: +{
+  "default": false,
+  "type": "boolean"
+}
    • addedInput schema / properties / wait_timeout
      Added value: +{
+  "default": 180,
+  "type": "number"
+}
  4. Addedv0.9.1
  5. Removedv0.8.9
  6. Changed6 schema fields changedv0.7.7
    • removedInput schema / properties / artifact_id / description
      Removed value: -"Optional specific artifact ID (uses latest if not provided)"
    • removedInput schema / properties / artifact_type / description
      Removed value: -"Type of artifact to download:\n- audio: Audio Overview (MP4/MP3)\n- video: Video Overview (MP4)\n- report: Report (Markdown)\n- mind_map: Mind Map (JSON)\n- slide_deck: Slide Deck (PDF or PPTX)\n- infographic: Infographic (PNG)\n- data_table: Data Table (CSV)\n- quiz: Quiz (json|markdown|html)\n- flashcards: Flashcards (json|markdown|html)"
    • removedInput schema / properties / notebook_id / description
      Removed value: -"Notebook UUID"
    • removedInput schema / properties / output_format / description
      Removed value: -"For quiz/flashcards only: json|markdown|html (default: json)"
    • removedInput schema / properties / output_path / description
      Removed value: -"Path to save the file"
    • removedInput schema / properties / slide_deck_format / description
      Removed value: -"For slide_deck only: pdf (default) or pptx"
  7. First observedv0.6.13

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden, and it adds little: it never says the tool writes to the local filesystem, that downloads are confined to a download directory, that authentication/notebook access is required, or that calls may block for minutes while polling. The artifact-type list is a capability inventory, not behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loaded: the core action leads, followed by scope and supported types. The multi-line type list is somewhat redundant with the schema but is compact and skimmable. No filler sentences.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and the schema covers all parameters well. What is missing is the context an agent needs to choose this tool correctly: differentiation from download_all_artifacts/export_artifact and any note about the filesystem-writing, potentially long-running nature of the call.

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 nine parameters in detail (output_path confinement, wait polling, artifact_type enum-like list, output_format). The description's type list overlaps with what the schema already states, adding no semantics beyond the structured fields. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb (download) and resource (NotebookLM artifact) plus the destination (a file), and the type list makes the scope concrete. It does not, however, distinguish itself from the close siblings download_all_artifacts and export_artifact, so an agent cannot tell from the description alone which of the three it should call.

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

Usage Guidelines2/5

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

There is no statement of when to use this tool versus download_all_artifacts or export_artifact, only the claim that it is a "unified download tool replacing 9 separate download tools". That historical note does not tell the agent which sibling to select in a given situation, and no prerequisites, exclusions, or conditions are given.

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

Deploy Server

Other Tools