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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), and the description adds genuinely non-obvious behavior: a provider error code (Spamhaus 127.255.255.x), timeout, or RFC 5782 test failure is reported as unavailable/unknown, explicitly NOT clean. It also discloses scope exclusions (domain-only DBL lists and score.senderscore.com excluded from IP checks) and the no-auth requirement.

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 purpose, then input rules, output contents, and edge-case semantics in logical order. Dense but justified given the tool's subtle unavailable-vs-clean interpretation. Slight redundancy remains: the response contents are described twice (answered/not-measured/disabled vs unavailable/disabled provider evidence).

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 and no schema-required params, the description shoulders the burden of explaining inputs, return values, and error interpretation — and covers all three thoroughly, including MX-resolution behavior and exclusions. Only minor gaps remain: unspecified behavior if both domain and ip are supplied, and no rate-limit or provider-count detail.

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%, so the baseline is 3; the description adds interaction semantics the JSON schema cannot express: ip and domain are alternatives, neither is individually required but at least one must be supplied (schema says required: 0), and domain triggers MX-IPv4 resolution while ip is a direct check. This meaningfully complements the field-level descriptions.

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 and resource ('Read-only query against the configured public DNSBL/RBL providers') and immediately describes the response shape. The DNSBL/RBL scope is unique among the ~44 siblings — no other tool targets blacklist providers — so an agent can distinguish it from check_spf, lookup_dns, and check_email_security without inspecting schemas.

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?

Provides an explicit use case ('Use for mail-server reputation triage') and a firm boundary ('it is not a delisting service'). Also gives operational selection guidance: domain→MX IPv4 resolution vs ip→direct check, with 'at least one is required.' It stops short of naming alternative tools for related reputation tasks, so not a 5.

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