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

Annotations already cover the safety profile (readOnly, idempotent, non-open-world), but the description adds materially more: the check is offline/instant with no DNS, registry or network call, and it catches script tricks only — not typos or digit swaps like paypa1.com — so a clean result is not a safety guarantee. That false-negative caveat is the kind of behavioral disclosure that changes agent behavior.

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 tight blocks: what it detects with an example, when to use it and the sibling overlap, then behavioral limits. The scoping caveat and the sibling exclusion are both front-loaded rather than buried, and no sentence is filler.

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?

For a single-parameter read-only checker with an output schema, the definition covers purpose, routing, offline behavior, and the false-negative boundary. Return values need only brief mention, which it provides ('scripts used and the Latin name it imitates'). Nothing needed to call it 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% for the single parameter, so the schema already documents acceptable input (Unicode or punycode, no full URL). The description restates the same scope ('one domain or Web3 name') and the раураl.com example illustrates the tool rather than adding parameter syntax beyond the schema. 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?

States a specific verb ('check') and resource ('one domain or Web3 name') and names the exact failure mode it detects (homograph / mixed-script look-alike) with a concrete example. It also implicitly separates itself from lookup_target, which is a sibling it explicitly references.

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 explicit use cases ('phishing triage, brand monitoring') and an explicit when-not: lookup_target already includes this warning, so there is no need to call both for one name. That is exactly the routing guidance an agent needs against a sibling.

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