Gemini Notebook by Chryzalide (agy-gemini-notebook-plugin)

notebook_research

Launch Fast, Deep, or Source Discovery research on a Gemini Notebook to gather web or Drive sources, optionally importing them for immediate querying.

Instructions

Launch a Fast Research, Deep Research, or Source Discovery session on a Gemini Notebook.

Allows the agent harness to pilot NotebookLM as an autonomous research engine:
- Set `create_notebook_title` to spin up a brand-new notebook before launching research.
- Set `mode='fast'` for rapid web/Drive search (~10-30s).
- Set `mode='deep'` for exhaustive multi-step Deep Research with a synthesized Markdown report.
- Set `mode='discover'` (or `'curious'`) for instant synchronous web source discovery.
- Set `source='web'` or `source='drive'`.
- When `wait=True` and `import_sources=True`, discovered sources are automatically imported
  into the notebook so you can immediately query or generate artifacts from them.

Input Schema

Name	Required	Default
`mode`	No	fast
`wait`	No
`query`	Yes
`source`	No	web
`timeout`	No
`cited_only`	No
`notebook_id`	No
`workspace_dir`	No
`import_sources`	No
`allow_duplicate`	No
`create_notebook_title`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 25, 2026

TDQS

A3.7/5.0

Behavior3/5

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

With no annotations, the description must carry the full behavioral burden. It discloses useful traits like approximate fast-mode duration, deep-mode output format, and source import behavior, but does not explain timeout behavior, side effects on existing notebooks, authentication needs, or what happens when wait=False.

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 front-loaded with the core action and then uses a tight bullet list to explain mode and parameter semantics. There is minimal fluff and every bullet conveys actionable information.

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?

For an 11-parameter tool with no annotations, the description is only partially complete. It covers the most important mode and import semantics, but several behavioral and parameter details an agent would need to call it correctly are missing, even though the output schema handles return values.

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 0%, so the description must compensate for all 11 parameters. It explains mode values, source values, wait/import_sources interaction, and create_notebook_title, but leaves cited_only, timeout, notebook_id, workspace_dir, allow_duplicate, and query undefined.

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 states a clear verb and resource (launch a research session on a Gemini Notebook) and distinguishes the three research modes. It does not explicitly compare itself to siblings like notebook_query or notebook_research_status, which keeps it from 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 Guidelines4/5

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

It gives explicit guidance for choosing between modes: fast for rapid search, deep for exhaustive multi-step research, and discover for instant synchronous discovery. It lacks when-not-to-use guidance or explicit alternative-tool routing, so it falls short of 5.

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