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

Goes well beyond the annotations (which only cover read-only/open-world/idempotent safety): it discloses that enrichment halts once availability is known so 'premium can remain null', that partial failures return received answers plus retry guidance with no automatic retries, and that cached mode makes zero provider calls. These are exactly the runtime behaviors an agent cannot infer from structured fields.

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 dense sentences, no filler; the core capability (one name, up to 20 extensions, shared evidence) is front-loaded, and each following sentence adds a distinct operational fact.

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 still covers the return-shape quirks an agent needs: nullable premium, partial-failure payloads with retry guidance, and no automatic retries. Nothing required to call or interpret it correctly appears 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%, so tlds and cachedOnly are already documented; the description adds the shared five-minute evidence window and reconfirms the 20-extension ceiling for tlds. It repeats rather than extends some cachedOnly semantics, keeping it just above the high-coverage baseline.

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 with scope: 'Check one name across up to 20 extensions', which immediately distinguishes it from the single-name sibling check_availability. The reusing-shared-evidence clause further pins down what this batch variant does.

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 closing sentence explicitly rules out related tasks – 'No selected-registrar fallback, fresh mode, prices or purchases' – and 'cachedOnly makes no provider calls' gives a clear condition for that mode. It stops short of naming the sibling tools to use instead (estimate_cost, get_tld_prices, check_availability), so routing is implied rather than explicit.

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