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

Annotations indicate readOnlyHint=false and destructiveHint=false, while idempotentHint=true. The description adds value by explaining the token's life span (permanent vs session-only), the two usage modes, and that calling with no args returns a link. It does not contradict annotations and provides behavioral context beyond what annotations already convey.

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 relatively compact for the complexity it covers, being front-loaded with the tool's purpose and the recommended permanent setup. It uses a compact structure with actionable steps, though it packs multiple clauses into a long first sentence, slightly hurting readability.

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 annotation set (idempotent, non-destructive) and the single optional parameter, the description covers the essential context: login flow, token usage, and the two modes. It even mentions an alternative setup (config header) and explains the session-only vs permanent distinction. However, it doesn't describe the returned link's format or failure scenarios, so a small gap remains.

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 has only one optional string parameter 'token' with 0% description coverage, so the description must compensate. It explains that 'token' should contain the JWT pasted by the user for session-only login, which adds meaning beyond the schema. However, it doesn't detail token format requirements or what happens if an invalid token is provided, so rich semantics are partially covered.

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: to authenticate an IDE agent (like Cursor) with the MCP.AI server by logging in via browser and obtaining an access token. It distinguishes itself from siblings by providing a specific authentication flow with setup options, though it does not explicitly contrast 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 explicit when-to-use guidance: it explains both permanent setup (adding a header to the server config) and session-only login (pasting the token). It also gives clear usage context—when to call with a token versus without args—and even clarifies when to use this tool versus alternatives (e.g., adding to config for permanent connection).

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