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

The annotations already establish that the operation is safe and repeatable (readOnlyHint, idempotentHint, destructiveHint=false). The description adds non-obvious behavior: a bare name with no zone fans out into checks across popular zones (.ru, .com, .net, .org), which tells an agent to expect multiple results per input. It does not explain the response shape or which 'прочих' zones are covered.

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?

Four short sentences with no filler, and the most important constraint ('Имена НЕ придумывает') comes before the hand-off to check_domains. Every sentence carries information the agent needs.

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?

Because there is no output schema, the description should ideally say what comes back: availability status, error, or zone results. Instead, the zone list is left vague with 'и прочих', and the return values are unaddressed. Suitable for a simple read tool but not fully 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%, so the baseline is 3, but the description adds real meaning beyond the schema: a zone-less input is interpreted as a name to try in several popular zones, so the agent knows one input can produce multiple checks. It is slightly at odds with the schema wording ('домен, несколько доменов через пробел'), which suggests a domain list rather than arbitrary text.

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 gives a concrete verb+resource: 'Достаёт доменные имена из произвольного текста и проверяет каждое'. It also distinguishes itself from the similar sibling check_domains by stating that it checks exactly what is named and that invented variants belong in check_domains.

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 makes it clear that this tool is for raw text input and that check_domains is the destination for a hand-built list of variants, including the exclusion 'Имена НЕ придумывает'. It does not address the other related siblings (check_domain, whois_domain, dns_records), so the guidance is clear but only partial.

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