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

It discloses behavior beyond annotations, such as the distinction between permanent non-expiring config-based bearer tokens and session-only pasted JWTs. It also implies a browser-login flow without contradicting idempotentHint or any other annotation.

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 compact and front-loaded, with two sentences covering auth flow, best practices, and invocation patterns. Slightly conversational phrasing adds minor noise but every sentence offers actionable value.

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 with one optional token parameter, no path schema, and idempotentHint true, the description is largely sufficient and explains how to obtain and use the token. It does not mention response shapes or errors, but these are not critical for this use case.

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?

Even though the schema only defines an optional 'token' string with no description, the description compensates by explaining that token should be the JWT pasted by the user and that omitting it returns the login link. This adds meaningful semantic context for the single parameter.

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: authenticate an MCP.AI connection by obtaining a login link or accepting a pasted JWT. It names specific actions and resources, though it does not explicitly compare itself with sibling tools like 'connect'.

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 concrete when-to-use guidance: call with no arguments to get the login link, call with { token: '<jwt>' } for session-only auth, or use the server config for a permanent bearer token. It lacks explicit sibling-tool alternatives, but the usage context is clear.

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