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

Substantial disclosure beyond the annotations: fixed Cloudflare DoH resolver, 7 queries per shared 8s window, 128KiB cap, no SMTP, no query storage, no DNS changes, and explicit 'unknown' semantics for missing selectors or inherited DMARC. The idempotentHint=false annotation is consistent with the warning that live DNS results vary. It stops short of 5 because much of the behavioral text is defensive boilerplate repeated around payment rather than crisp operational fact.

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?

Purpose is front-loaded, which is good, but the text is a dense wall that repeats the price twice ('0.005 USDC' then 'Price: 0.005 USDC'), packs a full x402 payment protocol into a tool description, and appends multiple disclaimer sentences. A large share of the content does not help an agent decide or invoke, so it fails the 'every sentence earns its place' test.

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 compensates by supplying an illustrative output excerpt showing spf.status, dmarc.status, dmarc.alignment_verified, mx.status and smtp_reachability, plus explicit unknown semantics. Coupled with rate limits and payment requirements, an agent has enough to call it correctly; only the illustrative (non-normative) nature of the return shape leaves a small gap.

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 0%, so the description carries the burden. It does clarify that 'domain' is a public domain and that 'selectors' are DKIM selectors the caller supplies, and provides a minimal input example plus the rule that absent selectors yield 'unknown'. However it never states that selectors is optional or capped at 3, and the maxLength/pattern constraints in the schema are unexplained in prose.

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 first sentence names a specific verb and a well-defined resource set: MX, SPF, direct DMARC, supplied DKIM selectors and resolver-reported DNSSEC evidence. An agent can immediately tell this is an email-authentication DNS observation tool. It loses a point only because it never references a sibling, and the closest-sounding sibling (security_check) is left un-contrasted.

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?

Usage is implied rather than stated: 'Observe a public domain's ... records' plus the caveat that 'Missing selectors and inherited DMARC policy stay unknown' and 'Published records and resolver AD are not proof of inbox delivery.' There is no explicit when-to-use/when-not or named alternative, so the agent must infer that this is the pre-check for domain-based mail posture.

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