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, idempotentHint=true, and openWorldHint=true. The description adds valuable context beyond this: it specifies the tool navigates to a Studio panel, extracts structured JSON, and returns specific table properties (headers, rows, totals). It also mentions error behavior when the table isn't ready. No contradictions with annotations.

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 well-structured with clear sections ('What This Tool Does', 'Returns', 'Requirements', 'Example'), each sentence adds value, and it's front-loaded with the core purpose. No redundant or verbose content.

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 read-only tool with rich annotations and no output schema, the description is complete: it explains the action, prerequisites, return structure, and error conditions. It compensates for the lack of output schema by detailing the return format, making it sufficient for agent use.

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?

Schema description coverage is 100%, with both parameters (notebook_id and notebook_url) fully documented in the schema. The description provides an example showing notebook_id usage but adds no new semantic details about parameters beyond what the schema already states. Baseline 3 is appropriate given high schema coverage.

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 clearly states the specific action ('Extract'), target resource ('Data Table content from a notebook'), and mechanism ('navigates to notebook's Studio panel, extracts table data as structured JSON'). It distinguishes from sibling tools like 'generate_data_table' by focusing on extraction rather than generation.

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 'Requirements' section explicitly states when to use this tool ('Data table must be generated first') and when not to ('Returns error if table is not yet ready'), naming the alternative tool ('use generate_data_table'). This provides clear guidance on prerequisites and alternatives.

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