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

Annotations already provide readOnlyHint=false and destructiveHint=false, but the description adds important behavioral context: that it involves browser login and token generation, that the token can be permanently configured, and that calling without args returns a link. It also implicitly communicates that this is an interactive flow requiring user action. This goes beyond the annotations, though it could disclose side effects like potential session persistence or security implications more deeply.

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 concise, two sentences long, and front-loaded with the tool's purpose. Each sentence adds value: first explains the core mechanism, second gives two usage paths. Slight room for improvement: some redundancy between 'log in in the browser' and 'call with no args to get the link' could be trimmed, but it's appropriately sized and not overly verbose.

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 has one optional parameter and no output schema, the description covers the essential flow: how to use it, both invocation modes, and the recommended permanent setup. It doesn't explain the return value (likely a link) explicitly, but that's inferable from 'get the link'. It also lacks details on error handling or token validation, but for a simple auth tool, it is adequately complete.

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 only defines a 'token' parameter with no description coverage (0%), so the description must compensate. It does: it explains the 'token' parameter is a JWT that the user pastes for session-only login, and that omitting it triggers a link generation. This adds semantic meaning beyond the bare schema, though it could specify format or constraints more explicitly.

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 with MCP.AI by logging in via browser and capturing an access token. It distinguishes itself from siblings by focusing on authentication, while siblings like 'connect' or 'marketplace' imply different actions. The verb 'authenticate' with explicit resource (MCP.AI) and method (browser login) is specific and unambiguous.

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 explicitly provides when to use this tool and how: it gives two usage modes (session-only with a token argument, or permanent with config header), and even instructs to call with no args to get the link. It also suggests the best practice (config header) and distinguishes between session and permanent options, covering alternatives within the tool's scope. It doesn't pit it against siblings but clearly defines usage scenarios.

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