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

The description discloses that passing a token results in a session-only login, while adding to config provides a permanent, non-expiring connection. This goes beyond the annotations (idempotent, non-destructive) by explaining the persistence of the authentication state.

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 verbose and slightly disorganized, starting with a vague phrase 'MCP.AI for IDE agents' before clarifying the purpose. Multiple alternatives and conditions are crammed into a single run-on sentence, making it harder to parse than necessary.

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 simple tool (no output schema), the description covers the main use cases: obtaining a link and authenticating with a token. It mentions both permanent and session-only options, which is sufficient context for a user to decide how to proceed.

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 one parameter 'token' with zero description, but the tool description explains that it expects a JWT token obtained from the login link. It also clarifies that the parameter is optional by stating you can call with no args to get the link. This sufficiently compensates for the missing schema description.

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 indicates this tool is for authentication to the MCP server, mentioning login and token usage. It distinguishes from siblings like 'connect' and 'report_bug' by focusing on credential handling.

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 usage instructions: either call with no args to receive a login link, or call with a token for session-only login. It implies when to use this tool (when authentication is needed) but does not explicitly compare to alternatives since none exist for authentication.

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