NotebookLM MCP Server (Security Hardened)

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

Annotations provide hints (e.g., readOnlyHint=false, destructiveHint=false), but the description adds valuable behavioral context beyond this: it discloses that the tool 'Opens the Studio panel in NotebookLM', 'Generation typically takes 1-3 minutes', and 'Returns immediately with status (check with get_data_table)'. This includes UI effects, timing, and output behavior, which are not covered by annotations. No contradiction with annotations is present.

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 sections ('What This Tool Does', 'Requirements', 'Example'), front-loading key actions. It is appropriately sized, but includes some redundancy (e.g., repeating 'Generate' in multiple points) and could be slightly more streamlined without losing clarity.

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?

Given the tool's complexity (involves UI interaction, async processing, and authentication) and lack of output schema, the description is mostly complete: it covers purpose, requirements, behavioral traits, and usage context. However, it does not detail error conditions or what 'status' entails, leaving minor gaps for an agent to infer.

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%, so the schema already documents both parameters (notebook_id and notebook_url) with descriptions. The description does not add meaning beyond the schema, such as explaining parameter interactions or usage nuances. With high schema coverage, the baseline score of 3 is appropriate as the description does not compensate but also does not detract.

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 tool 'generates a structured tabular extraction from notebook content' and 'tables organize key information from sources into rows and columns', specifying both the verb (generate) and resource (data table from notebook sources). It distinguishes from siblings like 'get_data_table' (which checks status) and 'add_source' (which adds content rather than extracting it).

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 context for when to use this tool: 'Notebook must have at least one source' and 'Authentication required (run setup_auth first)'. It also implies an alternative by noting 'Returns immediately with status (check with get_data_table)', but does not explicitly state when not to use it or compare to other extraction tools like 'generate_audio_overview'.

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