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

No annotations are provided, so the description carries the full burden, but it discloses a key behavioral trait: for Polish numbers, the address is reduced to the town due to GDPR. This is useful context. However, it does not mention other potential behaviors like rate limits, response time, or error handling. It also does not state that the tool is a read-only operation, but given it's a validation, it's likely inferred. The disclosure partially compensates, but more could be said.

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?

The description is concise, with two sentences. The main purpose is front-loaded, and the GDPR note adds value without being verbose. Slight deduction for not adding a hint about the enum or other structural hints, but overall efficient.

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 the tool's complexity (simple validation) and the rich schema (enums and descriptions), the description covers the core functionality and a key behavioral nuance. However, it lacks guidance on when to use this versus the sibling tools (e.g., sprawdz_nip) and does not mention potential error cases or alternative tools for batch checks (like sprawdz_lista_nip). The description is adequate but leaves some context gaps.

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 both parameters are already described in the schema: vatNumber (without country prefix) and countryCode (with enum). The description adds meaning by clarifying the GDPR-induced address truncation for Polish numbers, but this is not directly a parameter semantic - it's a behavioral detail. The description does not add new meanings to the parameters themselves, so a 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?

The description clearly states the tool validates EU VAT numbers in the VIES system, with a specific verb ('Validate'), a specific resource ('counterparty's EU VAT number'), and a mention of the European Commission. It distinguishes from siblings like sprawdz_nip (which likely checks Polish NIP) and sprawdz_regon (which checks REGON), as this is specifically for EU VAT. There is no tautology, and the scope is unambiguous.

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?

There is no guidance on when to use this tool versus alternatives. With siblings like sprawdz_nip and sprawdz_lista_nip, an agent might need to know whether to use this for Polish numbers or those for other EU countries, but no such direction is provided. The description does not mention exclusions or conditions, leaving the usage context entirely implicit.

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