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

Annotations include idempotentHint=true, which is partially reflected by the description mentioning 'non-expiring' and 'session-only' but not explicitly stating idempotency. The description adds behavioral context about the token expiration (permanent vs session) and the dual mode of authentication, which goes beyond the annotations. However, it doesn't disclose potential side effects like creating a session or invalidating previous tokens, but given idempotentHint=true, this is adequate.

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 paragraph that is informative but slightly dense. It front-loads the audience ('MCP.AI for IDE agents') and the core action ('log in in the browser'), but the sentence structure could be simplified for clarity. It earns its place with actionable steps, though it could be broken into bullet points for better scannability. Overall, it is concise with minimal waste.

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 tool's moderate complexity (two usage modes), the description covers the key aspects: the login flow, token acquisition, and both invocation paths. There is no output schema, but the tool likely returns a link or confirmation, which is implied. The description lacks details on error handling (e.g., invalid token), but the provided guidance is sufficient for an agent to orchestrate the authentication flow with the user.

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 parameter 'token' with 0% description coverage, so the description must explain its meaning. It does so: 'paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes'. It also clarifies what happens when no args are provided (get the link). This adds semantic meaning beyond the bare schema, but could be more explicit about token format validation, though not required.

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 that this tool is for authentication in MCP.AI, specifically for IDE agents. It distinguishes itself from siblings by describing the login flow (browser login, token copy) and the two ways to use it (config header vs. session token), which is a specific purpose not covered by any sibling names.

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: 'log in in the browser, copy the access token' and explains the best approach (add to config) versus session-only login. It also instructs when to call with no args to get the link, enabling the agent to prompt the user appropriately. This is strong usage guidance, though it does not explicitly mention when not to use it vs siblings, but siblings are unrelated.

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