NotebookLM MCP Server (Security Hardened)

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

Annotations already provide readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering safety and idempotency. The description adds valuable behavioral context beyond annotations: it reveals the tool uses browser automation (implying potential latency and UI interaction), mentions context overflow risks with large histories, and provides practical guidance on managing output size. While it doesn't specify rate limits or authentication requirements, it adds meaningful operational context that annotations don't cover.

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

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

The description is efficiently structured with clear sections: a purpose statement, bulleted use cases, a 'Context Management' section with parameter guidance, and practical examples. Every sentence earns its place by providing operational guidance or clarifying semantics. The information is front-loaded with the core purpose, followed by progressively detailed guidance. No redundant or verbose content exists.

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

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

For a tool with 7 parameters, no output schema, and rich annotations, the description provides excellent contextual coverage. It explains the tool's operational context (browser automation), use cases, parameter interactions, and practical considerations like context overflow. The main gap is the lack of information about return format (though examples imply JSON), but given the annotations cover safety and the description covers usage patterns well, this is a minor omission in an otherwise comprehensive description.

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

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

With 100% schema description coverage, the baseline is 3. The description adds significant value by explaining the semantic purpose of key parameters: it clarifies that preview_only gives 'a quick count before extracting full content', output_file 'exports to JSON instead of returning to context' to avoid overflow, and offset/limit enable 'pagination through large histories'. It also provides concrete usage examples showing how these parameters work together. This goes well beyond the schema's technical descriptions.

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

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

The description explicitly states the tool's purpose: 'Extract conversation history from a NotebookLM notebook's chat interface' using 'browser automation to navigate to a notebook and extract all Q&A pairs'. It clearly distinguishes this from sibling tools like get_query_history (which might be for different query types) or get_notebook (which retrieves notebook metadata rather than chat content). The verb 'extract' is specific and the resource 'conversation history/Q&A pairs' is well-defined.

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

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

The description provides explicit guidance on when to use this tool: for 'recovering previous research conversations', 'auditing what queries were made', 'understanding quota usage', and 'resuming context from previous sessions'. It also offers practical usage patterns through the 'Context Management' section and examples, showing how to use preview_only for quick audits, output_file to avoid context overflow, and offset/limit for pagination. This gives clear operational context beyond basic invocation.

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