Skip to main content
Glama

source_add

Add local files, URLs, pasted text, YouTube videos, or Google Drive documents to a NotebookLM notebook so they are processed and available for queries.

Instructions

Add a source (document, URL, text, YouTube video) to the current NotebookLM notebook.

Supported source types:

  • file: Upload a local file (PDF, DOCX, TXT, etc.). Audio (MP3, M4A…) is transcribed and images (JPG, PNG…) are read, so a voice memo or a photo of a whiteboard becomes a queryable source.

  • url: Add a web page URL

  • text: Paste text content directly

  • youtube: Add a YouTube video URL

  • google_drive: Add a Google Drive document link

The source will be processed and indexed for use in conversations.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source_type": "<source_type>"
    },
    "name": "source_add"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoURL (required for source_type="url", "youtube", "google_drive")
textNoText content (required for source_type="text")
titleNoOptional title/name for the source
file_pathNoLocal file path (required for source_type="file")
session_idNoSession ID to reuse an existing session
source_typeYesType of source to add
notebook_urlNoNotebook URL. If not provided, uses the active notebook.

Output Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.4

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the safety and mutation profile is covered. The description adds real value beyond that: audio files are transcribed, images are read/OCR'd, and the source is processed and indexed before use — non-obvious side effects an agent should anticipate. It stops short of discussing duplicate handling, failure modes, or auth requirements.

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?

Front-loaded purpose sentence followed by a scannable type list, then a short note on indexing. The bullets partly restate the schema enum, but each one carries added behavioral detail, so little is wasted. Slightly longer than strictly necessary but well organized.

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?

An output schema exists, so return values need not be described. For a 7-parameter mutating tool the description covers the essential decision surface (which type, what each type ingests, that indexing happens). Gaps remain around duplicate sources, notebook_url fallback behavior, and error conditions, but these are secondary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage the baseline is 3, but the description earns more by attaching behavioral meaning to source_type values (file → transcription/OCR, url vs youtube vs google_drive) and implicitly mapping which inputs are needed per type. It does not explain session_id or notebook_url defaults, which the schema alone carries.

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 description opens with a specific verb and resource ('Add a source ... to the current NotebookLM notebook') and enumerates the five concrete source types, so the agent knows exactly what the tool does. It never contrasts itself with plausible siblings such as library_add, note_to_source, or source_copy, which is the only reason it falls short of a 5.

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?

Usage is implied by the opening sentence and the per-type breakdown tells the agent which source_type to pick for a given input. However, there is no explicit when-to-use/when-not guidance and no mention of alternatives like library_add or note_to_source, so routing between similar tools is left to inference.

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