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

Annotations already cover read-only/idempotent/open-world safety, yet the description adds substantial behavioral detail: distinctions between NXDOMAIN, NOERROR-without-records and SERVFAIL, honest admission of partial/truncated evidence, the CDN/caching caveat, quota and cache-window behavior (30s, 5s for partial), keyless auth, and an explicit SSRF-style assurance that it never connects to answer addresses. That is far beyond what the structured fields convey.

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 'Use for...' purpose statement, then layered caveats, all in one dense paragraph. Every clause carries signal, though the caveat/quota tail is dense enough that an agent must read to the end to catch the evidence-quality limits.

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?

An output schema exists, so return-format explanation is unnecessary; the description instead covers the things the schema can't: error-code semantics, partial-evidence handling, caching windows, quota cost, and trustworthiness of record content. Nothing an agent needs to invoke or interpret this correctly appears to be missing.

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 coverage is only 50% — the 'name' param is documented in-schema, but the 'type' enum has no schema description. The description compensates by enumerating the record types and stating 'one record type per call (default A)', which is the key semantic an agent needs and is not in the schema.

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?

Opens with a specific verb+resource ('compare A/AAAA/CNAME/NS/MX/TXT/CAA records, TTL, DNS response codes and resolver-reported DNSSEC AD') across two named resolvers, so the scope is unmistakable. It implicitly separates itself from website/DNS-propagation concerns ('not worldwide propagation or multi-geo') but never explicitly contrasts with the sibling check_website, so it falls short of full sibling differentiation.

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?

'Use for public-domain DNS diagnosis' plus the explicit exclusion 'not worldwide propagation or multi-geo' tells the agent both when to reach for this tool and one case to avoid. No sibling alternative is named for the excluded cases, so the routing guidance is clear but not exhaustive.

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