MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already show idempotentHint=true and destructiveHint=false. The description adds behavioral details: calling with no args returns a link, calling with token sets a session token, and the permanent config option is recommended. It explains the token is a JWT and that the connection is non-expiring when set via config.
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 three sentences long, front-loaded with purpose. It contains necessary details but could be slightly more concise (e.g., 'log in' vs 'MCP.AI for IDE agents...'). Still, every sentence is informative and earns its place.
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 single optional parameter and no output schema, the description covers the core functionality well. It explains the two authentication flows (permanent via config, session via token) and how to invoke each. Missing details like error responses or what happens if already authenticated, but overall complete for the tool's simplicity.
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 coverage is 0% (no parameter description in schema). The description fully compensates by explaining the 'token' parameter: it is a JWT from the browser, and calling without it returns the login link. This adds essential meaning beyond the schema.
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 is for authentication, explaining the login flow and token acquisition. It distinguishes from sibling tools like 'connect' by specifying the method (browser login, token paste) and the permanent vs session options.
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 clear context on when to call with no args (to get the login link) vs with a token (for session login). It also mentions the best permanent method (config header). However, it does not explicitly state when not to use this tool or list alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes (notebook vs source vs note vs artifact vs sharing). Minor overlap exists between notebooklm_ask and notebooklm_history (both Q&A-related) and between artifact generate/poll/retry, but descriptions help differentiate. Meta-tools like marketplace and authenticate are separate in function.
Core tools follow a consistent notebooklm_{resource}_{action} pattern. However, meta-tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) lack the notebooklm_ prefix, breaking overall naming consistency. Within the core domain, naming is predictable.
43 tools is high but covers a broad domain: notebooks, sources, notes, artifacts (multiple types), sharing, Q&A, plus meta-tools. Some tools could be merged (e.g., share_add/remove/update/view_level), and meta-tools inflate count. Feels slightly heavy but not excessive for the feature set.
Covers full lifecycle for notebooks, sources, notes, artifacts (CRUD plus generate, download, poll, retry, suggestions). Sharing and Q&A have comprehensive operations. Minor gap: no tool to update notebook metadata beyond rename, but overall very complete.