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

Annotations only declare idempotentHint and non-read-only, so the description carries the burden of disclosing side effects. It adds value by revealing that the config approach yields a 'permanent, non-expiring connection' while the token path is 'session-only', and by describing the agent's expected orchestration steps (call with no args → give user link → await token). It does not conflict with the annotations; in fact, it's consistent with idempotent behavior when called with no args.

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?

Three dense sentences walk through purpose, recommended config approach, and session fallback in a logical order, with every clause earning its place. The structure is slightly run-on — the third sentence crams two call patterns behind a colon — but the 'Best:' and 'Or' signposts keep the flow readable.

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?

With no output schema, one optional string param, and moderate workflow complexity (browser round-trip), the description covers all key call patterns: no-args, token-pasted, and config-based. It would be more complete with explicit return-value or error examples (e.g., expired/invalid token), but for an auth handshake tool the critical behaviors are all disclosed.

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 — and it does. It explains that 'token' is a JWT the user pastes after browser login, and clarifies the optionality ('call with { token: "<jwt>" }' versus 'no args to get the link'). It could add token format/expiry details, but it conveys the key semantic: token is omitted to retrieve the link, then passed to complete login.

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 opens with a specific verb+resource pair ('log in in the browser') scoped to 'MCP.AI for IDE agents (Cursor, etc.)', making the tool's purpose unmistakable. It clearly explains the authentication flow (browser login → copy token → pass or configure), distinguishing it from siblings like 'connect' by centering on the token/cookie handoff. The two call patterns (config vs. session) further clarify what this specific tool does.

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 when-to-use guidance by contrasting the 'Best' permanent config approach with the session-only paste fallback, and tells the agent exactly when to pass the token vs. call with no args. It could be stronger by explicitly naming the 'connect' sibling as an alternative, but the context for when to use this flow is clear.

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