save_auth_tokens

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It reveals that the tool saves cookies, that some parameters are deprecated/auto-extracted, and that it's a fallback. However, it does not disclose the side effects of saving (e.g., where cookies are stored, whether they overwrite existing ones, or if authentication state is updated). The basic safety profile is implied but not fully detailed.

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 bold fallback note, an 'IMPORTANT FOR AI ASSISTANTS' section, and bullet-style parameter explanations. It is front-loaded with the most critical guidance. However, it repeats the same instruction ('First, run nlm login') twice and uses redundant phrasing, making it slightly less concise than ideal.

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 existence of an output schema (not shown), the description need not explain return values. However, the tool is a fallback authentication method with 5 parameters. The description covers usage order and parameter roles but omits what happens after saving (e.g., whether authentication state is updated, if the tool can fail, or how to verify success). For a fallback tool, these gaps could hinder proper 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?

The input schema has 0% description coverage, so the description must add meaning. It explains that 'cookies' is only needed if CLI fails, that 'csrf_token' and 'session_id' are deprecated and auto-extracted, and that 'request_body' and 'request_url' are optional for manual extraction. This provides significant context beyond the plain schema types and null defaults.

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 as saving NotebookLM cookies as a fallback authentication method. It distinguishes itself by emphasizing that it should only be used if the automated CLI (nlm login) fails. The verb 'save' and resource 'NotebookLM cookies' are specific, and the fallback context is clearly conveyed.

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 explicitly instructs the AI to first run 'nlm login' via Bash/terminal and only use this tool if that fails. This provides clear when-to-use and when-not-to-use guidance, and the alternative is named. The instructions are actionable and prevent misuse.

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