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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds real behavioral context on top: answers come from public resolvers (Cloudflare 1.1.1.1), cached results can lag a DNS change by its TTL, and whois data comes from the public RDAP registry. It stops short of discussing failure modes, rate limits, or behavior for non-existent domains or failing DKIM selector lookups.

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?

Front-loaded with the enumeration of check modes, and nearly every clause maps to a distinct mode or caveat, so little is wasted. It is a dense wall of parenthetical clauses crammed into one paragraph, which costs a bit of scannability but not accuracy.

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?

For an eight-mode tool with no output schema, the description explains what each mode yields (records, registrar/status/expiry, issuer/expiry/days-left, hostname behind an IP), which is what an agent needs to choose and trust the call. Minor gaps remain on error/empty-result behavior and the exact shape of each mode's response.

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?

With 80% schema coverage the baseline is 3, and the description earns a bump by explaining behavior the schema cannot: default record type A, the fallback selector list tried when dkim_selector is omitted, and the mode-to-parameter binding (ip for reverse_dns only). The `domain` parameter still only gets 'bare domain' from the schema, so the description is not fully exhaustive.

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 (live DNS/domain checks) and enumerates the exact resource facets it returns (records, SPF/DMARC/DKIM, registrar/expiry, certificate, PTR). It explicitly scopes itself to 'ANY public domain (not only account sites)', which separates it from the account-oriented siblings like get_site_health and verify_site.

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?

Maps each `check` value to a concrete use (dns = one record type, mx/ns/txt = that record set, email_auth = SPF+DMARC+DKIM, whois, ssl, reverse_dns), so the agent knows which mode to pick. It also names the alternative for account sites — 'get_site_health already holds the daily audit' — giving an explicit when-not-to-use route.

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