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

Annotations already mark the tool as read-only and idempotent, and the description adds valuable behavioral context: it is offline, does not call VIES, returns a checksumChecked flag to distinguish verification strength, requires no wallet or API key, and has specific pricing/credit-token requirements. There is no contradiction with the annotations.

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 dense but efficient, front-loading the core question and then covering scope, limitations, input, and commercial terms in a compact form. The opening rhetorical question and the explicit 'Required input: vat' line are minor redundancies, but overall every section earns its place.

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 tool with a fully described schema, an output schema, and safety-oriented annotations, the description provides all decision-relevant context: offline behavior, checksum semantics, no VIES registration claim, required input, and auth/pricing details. An agent can correctly invoke this tool without additional inference.

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?

The input schema already defines vat as 'VAT number', so schema coverage is 100%. The description adds meaning by clarifying it must be an EU VAT number and explaining the validation logic applied to it: country prefix, national format, and check-digit algorithm. The 'Required input: vat' line is redundant, but the extra semantic context is useful.

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 states a specific verb and resource: 'Validate an EU VAT number offline', with concrete scope (country prefix, national format, and published check-digit algorithm for specified countries). It also disambiguates from a VIES registration check, which is the main confusion point for VAT tools, even though it does not name a sibling tool.

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 explicitly says when not to use it: 'Registration is deliberately NOT claimed' and directs to VIES as the only source for registration status. It also distinguishes checksum-verified results from format-only results. However, it does not explicitly reference sibling tools or state a positive 'use this when...' directive, so the when-to-use guidance remains somewhat implied.

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