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

Adds substantial behavior beyond the annotations: the email-plus-button handshake, the requirement that opening the page alone does nothing, the 'Yes, connect' step, that no key is shown in the browser, a rate limit of 5 per email per hour, and a 15-minute link expiry. These are exactly the operational constraints an agent needs and cannot infer from readOnlyHint/destructiveHint/openWorldHint.

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?

Dense but front-loaded around the core action, and every clause carries operational value (flow steps, userCode handling, rate limit, expiry). The mid-sentence flow narration makes it slightly run-on, but there is little throwaway text.

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?

With no output schema, the description supplies what the tool returns (userCode, pollToken) and how those outputs are consumed downstream, plus timing and quota limits. Nothing an agent needs to invoke and follow through correctly is missing.

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?

Schema coverage is already 100%, so the baseline is 3; the description earns extra by stressing the non-obvious constraint 'Ask for the user's email, do not invent one' and by tying the returned value (userCode, pollToken) back to what the user must supply. It does not add format/syntax detail beyond the schema, so it is not a 5.

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?

States a specific verb+resource (start signup) and immediately differentiates from the sibling by naming check_signup and its role ('That lets check_signup return an API key for this MCP client'). An agent can tell the two apart without opening either schema.

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?

Gives clear contextual guidance: ask for the email rather than inventing one, complete the browser flow, and hand the userCode back so check_signup can produce the key. It stops short of explicitly excluding cases (e.g., 'skip this if a key already exists'), so it is strong but not fully exhaustive on when-not-to-use.

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