Login to Neuron

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

Annotations only set destructiveHint=false, which is consistent. The description adds valuable context: the recommended mode shares no credentials, while legacy mode exposes credentials to the AI. This goes beyond what annotations provide, though it doesn't specify what the tool returns upon success.

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 extremely concise: two sentences and a list. Every sentence adds value, and the most critical information (purpose and modes) is front-loaded. No waste.

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 simple authentication tool, the description covers the modes well but omits the output or side effects. With no output schema, the agent might need to know what token/session is returned. However, given the tool's simplicity and common pattern, the gap is moderate.

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 zero parameters (100% coverage), so the description carries the full burden. It adds meaning by describing three implicit parameter scenarios (none, token, email+password), which is helpful for an agent to understand invocation patterns.

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 'Authenticate with Neuron' and enumerates three distinct modes (no args, token, email+password). It uses specific verbs and distinguishes the tool's core purpose from sibling tools, none of which are login-related.

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 guidance on when to use each mode, recommending the no-args browser option for security. However, it does not explicitly state when not to use the tool (e.g., if already logged in) or mention alternatives like refresh_token.

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