lookup_registration

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description aligns by stating 'Observation only: no record is composed.' It then adds substantial context beyond the annotations: redacted:true is the normal post-GDPR outcome rather than a failure, unknown means the registry did not answer (not absence) with a reason field distinguishing rate-limit/timeout/error/no-RDAP-service, and the instruction to report rather than advise. No contradiction with annotations.

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?

A single dense paragraph, but every clause earns its place: the front-loaded trigger, the RDAP field inventory, the redacted-normal caveat, and the critical guardrails about status semantics and buy-advice. It is long but information-dense with no filler; a slightly more structured layout would push it to a 5, but the density is justified for a decision-relevant lookup tool.

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 carries the full burden of explaining the return semantics, and it does so thoroughly: enumerates the returned fields (registrar with IANA id, dates, EPP status codes, nameservers, DNSSEC delegation, abuse contact), defines all three status values, and covers failure modes (rate limit, timeout, registry error, TLD without RDAP). Nothing an agent needs to interpret the response correctly is 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 100% — the schema already documents the domain parameter thoroughly (format, bare names and subdomains accepted, punycode normalization, exclusion of scheme/path/port). The description adds no parameter-specific detail beyond what the schema provides; its extra information concerns response semantics (status values, reason), which belongs to behavioral transparency rather than parameter semantics. Baseline 3 is 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?

Opens with a precise trigger condition ('Use this when the user asks who owns a domain... the WHOIS question') and names the specific operation: read a domain's registration from the registry over RDAP. The verb+resource is unmistakable, and no sibling tool performs WHOIS/registration lookup, so it distinguishes itself clearly without needing to name an alternative.

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?

Gives an explicit when-to-use with a concrete list of triggering questions (ownership, expiry, registrar, nameservers, registration status, transfer/delete locks). It also adds strong post-call behavioral guidance — never advise buying on pendingDelete, never claim a name is free unless status is exactly not_registered. It stops short of naming specific sibling alternatives or when-not conditions, which keeps it at a 4 rather than a 5.

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