validate_vat

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

With no annotations provided, the description carries the full behavioral burden. It usefully discloses that the live VIES step is an external EU-official call performed only after the free local check passes, signaling latency/cost, but it omits rate limits, auth requirements, error behavior, and return format — all relevant for a network-backed validation tool.

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?

Two front-loaded sentences that lead with the action name, with the enrichment (local then live) stated first. The bilingual duplication roughly doubles length but the content is efficient and there is no 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?

With no output schema and no annotations, the description must carry more, yet it stops at the two-stage flow. It does not describe what a validation result looks like, how errors surface (despite a get_error_codes sibling existing), or how cache and VIES affect the outcome, leaving real gaps for a 5-param external-API tool.

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 description coverage is 100%, so the schema already documents vat, live, useCache, vatNumber, and countryCode. The description adds no format/syntax detail beyond what the schema provides, so baseline 3 applies.

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 (validate) and resource (VAT / tax ID number), and describes a concrete two-stage behavior: free local format check followed by optional live VIES verification. It implicitly distinguishes itself from the format-only sibling by mentioning the live verification step, but never names check_vat_format, so the sibling boundary is left for the agent to infer.

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 staged description ('先做免费本地格式校验，再按需调用 VIES') implies when the live call fires versus when the cheap local check is enough, which indirectly guides the `live` flag. However, it never explicitly states when to prefer this tool over check_vat_format or when not to use it, leaving the alternative routing unstated.

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