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

The description adds substantial context beyond annotations: it explains the token is a JWT, that the connection is 'permanent, non-expiring' when configured, and that calling with no args returns a login link. This goes far beyond the annotations (readOnlyHint false, idempotentHint true) and provides crucial behavioral details about state and side effects.

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 front-loaded with the tool's purpose and flows logically from permanent to session-login use cases. It's slightly run-on with multiple clauses separated by colons and commas, but every sentence adds value without fluff.

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?

For a tool with only one optional parameter and no output schema, the description covers all necessary aspects: setup, invocation (with and without token), configuration persistence, and example invocation. It anticipates user needs around security and session permanence. No output schema exists, so no return-value documentation is expected.

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?

Despite 0% schema description coverage, the description fully explains the single 'token' parameter: it's an optional JWT used for session-only login, and omitting it returns a login link. It also explains workflow context (paste token) that the schema lacks, effectively compensating for the schema's lack of annotations.

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 function: 'log in in the browser, copy the access token' for MCP.AI. It specifies the resource (IDE agents like Cursor) and provides a concrete verb-noun structure. It distinguishes itself from siblings like 'connect' by focusing on authentication via browser login and token exchange.

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?

It explains when to use the token parameter vs no arguments ('call with { token: "<jwt>" } after the user pastes, or with no args to get the link') and differentiates permanent (config) vs session-based login. However, it doesn't explicitly contrast with alternative sibling tools like 'connect', so it stops slightly short of full when/not guidance.

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