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

Annotations already signal idempotent, non-read-only, non-destructive behavior. The description adds valuable context beyond those annotations: permanent vs. session-only scope, the non-expiring nature of the config-header approach, and the behavior of calling with no args to retrieve a link. It does not cover error cases, but that is not a major gap given the simple optional-token schema.

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 and front-loads the primary action. Each sentence earns its place by covering a distinct mode: browser login/token acquisition, permanent config-header setup, and session-only token/no-args behavior. Minor informality in phrasing does not undermine clarity.

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 absence of an output schema, the description does enough to convey the invocation modes and expected outcomes: config-header login is permanent, token login is session-only, and no-args returns the link. It could describe the response shape after successful token submission, but the optional single-parameter interface is simple enough that the current guidance is sufficient for correct 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 schema provides no description for the optional token parameter, so the description carries the burden. It explains that token should be the JWT pasted by the user and that omitting it triggers the link-retrieval flow. This compensates well for the schema's 0% description coverage, though it could be slightly more explicit about the expected JWT format.

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 with MCP.AI by having the user log in through a browser and obtain an access token. It also explains the two delivery modes (permanent config header vs. session-only token parameter), which distinguishes it sharply from sibling tools like connect or show_version.

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 gives explicit usage guidance: for a permanent connection, configure the Authorization header; for session-only login, pass the pasted JWT as { token: "<jwt>" }; with no args, get the login link. It does not name sibling alternatives, but no other sibling serves an authentication role, so exclusions are not necessary.

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