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

Annotations already signal readOnly/idempotent/non-destructive, and the description adds valuable behavioral specifics: the computation includes edit distance, apex/TLD diff, and homoglyph substitution with concrete substitutions, and the result flags are is_likely_typosquat and is_likely_lookalike with drivers. Stating 'no DNS query' clarifies there are no network side effects, which is beyond annotation semantics.

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?

Three sentences deliver the purpose, the algorithmic internals, and the key caveat without filler. The most selection-relevant information (compare, no DNS query) is front-loaded.

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 there is no output schema, the description usefully names the output flags and drivers, plus the computed dimensions. It doesn't fully specify the response shape or define 'drivers,' but for tool selection and invocation the inputs, outputs, and side-effect boundary are sufficiently covered.

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 already documents both parameters with descriptions and examples (target: 'Suspect domain, e.g. striipe.com'; reference: 'Known-good domain, e.g. stripe.com'), and description coverage is 100%. The description merely mirrors this relationship rather than adding new constraints, formats, or default behavior.

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 names a specific action ('Compare a target domain against a reference') and a concrete detection purpose (phishing/typosquatting/lookalike). It distinguishes dns_compare from the many dns_* siblings by closing with 'Pure analytical comparison — no DNS query,' so an agent can select it without opening 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?

Explicitly frames this as pure analytical comparison and rules out DNS querying, which prevents confusion with dns_lookup/dns_history/dns_profile. It neither lists alternatives by name nor gives a when-not-to-use rule (e.g., 'for resolution use dns_lookup'), but the exclusion plus sibling context supplies adequate guidance.

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