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

Annotations already cover readOnly, openWorld, idempotent, and non-destructive. The description adds useful context: 'No side effects', 'Returns all matching records currently in effect', '4-hour cache', and 'Verified source: Cloudflare DoH'. These details go beyond the annotations and help the agent understand caching and data freshness, so a 4 is warranted.

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 informative and front-loaded with the core purpose, but it is somewhat verbose, including a long feedback instruction block at the end. That block is useful but could be seen as auxiliary. Overall, it is organized with parameter labels and a clear usage note, so a 4 is fair.

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?

The description covers the essential call context: source, caching, return behavior, and an alternative tool. There is an output schema present, so return structure need not be described. The only notable gap is the `record_types` required contradiction, which could cause misuse. But for a read-only tool with rich annotations and a schema, the description is otherwise complete.

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 100% for both parameters, so the description's parameter restatements add little. However, the description states 'record_types: ... Required.' while the input schema clearly marks it as optional with a default (required is only `domain`). This is a direct contradiction that misleads the agent into thinking `record_types` is mandatory. Although the description does list valid values and an example, the incorrect 'Required' label outweighs that benefit, making 2 appropriate.

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 starts with 'Fetch current DNS records for a domain via Cloudflare DNS over HTTPS', clearly stating the verb, resource, and source. It differentiates from the sibling `domain_fetch_domain_rdap` by explicitly naming it as the alternative for registration metadata, making the tool's scope unambiguous.

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?

The description provides explicit guidance: 'Use this when you need live DNS resolution. Use domain_fetch_domain_rdap instead when you need registration metadata not DNS records.' This directly tells the agent when to use this tool versus the sibling, covering both inclusion and exclusion conditions.

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