NotebookLM MCP Server

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that CSRF and session ID are 'auto-extracted' from request components, which is useful behavioral context about how the tool processes inputs. However, it doesn't disclose important traits like whether this operation requires specific permissions, what happens to existing tokens, whether it's idempotent, or what authentication state changes occur. The description adds some value but leaves significant gaps.

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 a clear purpose statement followed by an 'Args:' section detailing each parameter. Each sentence serves a purpose: the first states the tool's function and auto-extraction behavior, while parameter descriptions explain sources and deprecation status. Some minor verbosity exists in repeating 'auto-extracted' concepts, but overall it's efficiently organized.

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 authentication-focused purpose, 5 parameters with 0% schema coverage, no annotations, but with an output schema present, the description provides reasonably complete context. It explains what the tool does, how parameters relate to each other (deprecation relationships), and data sources. The output schema existence means return values don't need description. However, for an authentication tool with potential security implications, more behavioral context would be beneficial.

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 0% schema description coverage for 5 parameters, the description provides crucial semantic information. It explains that 'cookies' should come from 'Cookie header from Chrome DevTools get_network_request', clarifies that csrf_token and session_id are deprecated and auto-extracted, and specifies that request_body and request_url are optional sources for token extraction. This adds substantial meaning beyond the bare schema, though it could provide more detail about expected formats.

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's purpose: 'Save NotebookLM cookies' with the verb 'save' and resource 'cookies'. It distinguishes itself from sibling tools by focusing on authentication token management rather than content creation or notebook operations. However, it doesn't explicitly contrast with any specific authentication-related siblings since none appear in the list.

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 implies usage context through references to 'Chrome DevTools get_network_request' and auto-extraction from request components, suggesting this tool is used when capturing network traffic for authentication. However, it doesn't provide explicit guidance on when to use this tool versus alternatives (like manual token management or other auth methods) or any prerequisites for successful operation.

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