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

Annotations declare the mutation profile (readOnlyHint=false, idempotentHint=false), but the description adds material context they don't carry: payment is required via x402 stablecoins, the secret is returned once and must be kept, and mail delivery only begins after settlement. It stops short of covering post-expiry behavior, name-collision errors, or irreversibility of the purchase.

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?

Three tightly packed sentences that lead with what the tool does, then the payment mechanism, then the return-value caveat. No filler; every clause carries operational information.

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 correctly discloses the return shape (inbox id plus one-time secret) and the payment prerequisite. It omits edge cases an agent would need — name-taken handling (which ties to the check_name sibling), what happens when the duration expires, and whether purchase is refundable.

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 description coverage is 100%: the 'name' parameter already documents the random fallback and 'duration' already carries the 1h/4h/24h enum. The description mostly restates these, adding only the resulting address format, so the baseline 3 applies.

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 ('Buy an email address') with concrete scope (1h/4h/24h) and the exact address format produced. An agent can distinguish this from siblings like check_name (availability), extend_inbox (renewal), and delete_inbox without opening any 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?

Clearly describes the two-step invocation protocol: call without payment to obtain a quote, then call again with the signed payment in _meta. It gives strong invocation context but never names siblings (e.g. check_name for verifying a desired name, extend_inbox for renewing) or states when not to use this tool.

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