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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description reinforces these but adds non-obvious behavior: 'Verified source: Cloudflare DoH. 4-hour cache' and 'Returns all matching records currently in effect.' This provides useful context beyond the structured annotations, though it does repeat some annotation content.

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 dense and front-loaded with the core action, then adds parameter details, usage guidance, source, cache, and a feedback fallback. While it redundantly restates annotation hints ('Read-only. No side effects. Idempotent.'), the additional clauses earn their place by covering valid values, usage alternatives, and data freshness.

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?

Given the rich annotations, output schema, and simple parameters, the description covers all necessary guidance: what it returns, when to use it, alternatives, valid inputs, and cache behavior. The only minor gap is potential error cases, but these are adequately handled by the output schema.

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 schema's record_types property says 'Optional' while the required array includes it; the description resolves this by explicitly marking both domain and record_types as Required and enumerating the valid record types (A, AAAA, MX, TXT, NS, CNAME, SOA) with an example. This meaningfully adds value beyond the schema, which lacks enums and misstates optionality.

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 a clear specific action: 'Fetch current DNS records for a domain via Cloudflare DNS over HTTPS.' It distinguishes this tool from sibling domain_fetch_domain_rdap by explicitly stating it's for DNS records, not registration metadata, leaving no ambiguity about the tool's role.

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?

Explicitly states 'Use this when you need live DNS resolution' and then directs to domain_fetch_domain_rdap for registration metadata. It also adds context about the source and cache (4-hour cache), helping the agent decide whether freshness is acceptable.

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