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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is partly covered. The description still adds genuinely useful behavioral context: per-call pricing ($0.0009 USDC via x402), the unpaid-call returns payment requirements rather than data, the retry mechanisms (X-PAYMENT / PAYMENT-SIGNATURE header or _meta["x402/payment"]), and that email-shaped values are redacted. Not contradicted by annotations, but the 'authorized domains only' restriction is left unexplained – the agent cannot tell what qualifies.

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?

Densely front-loaded: capability first, then scope limits, then output fields, then cost and payment mechanics. Every sentence carries information, though the payment sentence is long and mixes three ideas (cost, fallback response, retry options) that could be split for scanning.

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 usefully names the return fields (status, TTL, authenticated-data flag), and it covers the non-obvious payment failure mode. The main gap is the undefined 'authorized domains' set – an agent has no way to know whether its target domain is permitted before spending a call.

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%, so both params are already documented with type constraints and defaults. The description echoes the 'up to four record types' cap and adds the ASCII/punycode and no-URL/no-email domain constraint, but those largely restate the schema. Baseline 3 applies since the schema does the heavy lifting.

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 states a concrete resource and mechanism: 'Public DNS records over Google DoH,' plus what comes back (up to four record types, DNS status, TTL, authenticated-data flag). It implicitly carves itself away from email verification tools via 'no SMTP or mailbox verification,' though it does not name the sibling (email_domain_check) that covers that case.

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 gives clear operating conditions: authorized domains only, and explicitly that SMTP/mailbox verification is out of scope, which steers the agent to a different tool for email checks. It also explains the x402 payment path and the retry-with-header behavior. What's missing is an explicit named alternative and guidance on which record types to pick for which question.

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