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

The description discloses important behavioral aspects: the 'permanent, non-expiring' nature of the config-based auth and the 'session-only' semantics of token passing. It also hints at side effects (changing authentication state). Annotations already mark idempotentHint=true, which aligns; no contradiction. Slightly more could be said about token revocation or security, but the key behaviors are transparent.

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 dense and runs on, mixing instructions for the agent, the user, and the implementation. It packs a lot of information into two long sentences, which could be better organized (e.g., bullet points). Still, every detail serves a purpose, and there's no fluff, but it's not the most readable. A 3 reflects adequate but not exemplary structure.

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 an authentication tool, the description covers the main flows (permanent vs. session, with/without token) sufficiently. It explains how to obtain a token and the persistence trade-offs. It does not explicitly handle error cases (e.g., invalid token) or mention timeouts, but given the tool's simplicity and lack of output schema, it's reasonably complete. The sibling list includes 'connect' and 'marketplace', and while not explicitly contrasted, the description doesn't confuse them with authentication.

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 provides only a parameter name 'token' with no description or type constraints, yielding 0% schema coverage. The description compensates fully by explaining that 'token' takes a JWT pasted by the user and that omitting it returns a login link. This exactly addresses what the parameter means and how to invoke the tool, making it excellent despite the sparse 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 identifies the tool as an authentication mechanism for MCP.AI, explaining it logs in via browser and uses an access token. It's specific about the resource (authentication) and the two modes (config header vs. session token). However, it doesn't explicitly contrast with sibling tools like 'connect', so while purpose is clear, sibling differentiation is implicit.

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 usage context by explaining two paths: permanent (server config) and session-only (passing token) with a fallback to get a link. It implies when to use each method but doesn't explicitly state 'use this instead of X'. The guidance is practical and decision-oriented, earning a 4.

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