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

With no annotations, the description carries the full burden. It discloses payment requirement, the DNS-over-HTTPS mechanism, and explicitly warns 'not a guaranteed inbox verdict', which sets expectations about certainty. It does not disclose rate limits or failure modes but provides key behavioral context beyond basic mutation/read hints.

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 three sentences, front-loaded with the core purpose and signals, followed by the payment details. It avoids unnecessary filler and every sentence contributes either to purpose, limitation, or payment flow. The format is readable and scannable.

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?

The tool has moderate complexity (payment flow, multiple signal categories) and no output schema, so the description needs to explain both input semantics and what the agent will receive. It lists the signal types and the payment terms, which covers most of what a caller needs to know. It lacks explicit output structure (like field names) but is otherwise comprehensive for an AI agent.

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 input schema already provides full descriptions for both email and x_payment, including the payment flow semantics. The description adds no new parameter-specific details beyond what the schema states, so it neither increases nor decreases the baseline. The payment flow is mentioned in both places, but the schema's x_payment description is equally informative.

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 opens with 'Deliverability signals for one address' and enumerates specific checks (RFC5322 syntax, MX/SPF/DMARC, disposable/role flags), making it clear this is an email-specific verification tool. It distinguishes from siblings like domain_intel by scoping to a single address. The limitation note further clarifies scope.

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 explains the two-step payment workflow (call without x_payment to get terms, then call again with signed payment), and points to the free pricing tool as an alternative for seeing all prices at once. However, it does not provide explicit guidance on when to choose this tool over related siblings like domain_intel or address_screen, leaving that inference to the agent.

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