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

Annotations are sparse (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the description carries most of the behavioral burden. It adds valuable context: the browser-based flow, the permanent vs session distinction, and that no-args returns a link. This doesn't contradict the idempotency hint (authenticating is a set-once operation). It could add what happens on repeated no-arg calls or invalid-token failure, but for an auth tool the core behavior is well disclosed.

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 a single dense paragraph with every sentence earning its place: purpose, config mode, session mode, and no-arg behavior are all covered without filler. It's slightly verbose with technical parentheticals (Cursor, JWT), but the density is justified by the need to explain two distinct auth paths.

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 tool (1 optional param, no output schema), the description is nearly complete. It explains invocation for all cases (no args, with token), the permanent vs session behavior, and implies the return for the no-arg call ('to get the link'). Minor gaps: no mention of failure modes (invalid token, expired link) or what a successful token call returns. Overall adequate given the tool's low complexity.

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?

Schema description coverage is 0%, so the description must compensate. It explains the lone 'token' parameter as a JWT pasted by the user for session-only login, and clarifies that omitting it triggers the link-generation path. This is sufficient semantic context for the single optional parameter, though it could more explicitly state the token's format constraints.

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 states a specific action ('log in in the browser, copy the access token') targeting the MCP server connection, with two clear delivery modes (permanent config header vs session-only token). This clearly distinguishes it from sibling tools like 'connect' and 'marketplace' by focusing on the authentication mechanism rather than generic connection or discovery.

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?

Explicit, actionable guidance is provided for each mode: 'Best: add it to this server's config as a header' for permanent auth, 'call with { token: "<jwt>" }' for session login, and 'with no args to get the link' for initial setup. It even explains the trade-off (permanent non-expiring vs session-only), giving the agent clear decision criteria for which invocation pattern to use.

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