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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the description's job is to add context — it does, explaining the decision output, the plain-English reasons, the specific fraud patterns detected, and that live=true performs an external VIES registry lookup (consistent with openWorldHint). It does not mention latency, rate limits or failure behavior when VIES is unreachable, which is the main remaining gap for a network-dependent 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?

Front-loaded with the decision ('One call before paying a supplier') followed by what is checked, what it catches, and the minimal-input rule. It is dense but every sentence carries distinct information; no restatement of the name or title.

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?

There is no output schema, so the description must carry the return contract — and it does, naming the three verdict values and the accompanying plain-English reasons. Combined with the fraud patterns and the live-lookup caveat, an agent has enough to call and interpret the result without further documentation.

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 all eight fields and baseline would be 3. The description adds non-obvious semantics the schema cannot express: all fields are optional and 'only one field is needed', and the tool degrades gracefully on partial invoice data — that materially changes how an agent should populate the arguments.

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 ('validates the IBAN, BIC, VAT and EIN ... cross-checks them against each other') and a concrete output ('verdict pay / review / hold'), which cleanly separates it from the single-field siblings validate_iban, validate_bic, validate_eu_vat, validate_gb_vat and validate_ein. An agent can tell this is the aggregate/combined check without opening any schema.

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?

'One call before paying a supplier' gives clear situational context, and 'Pass whatever the invoice has; only one field is needed' tells the agent how to invoke it with partial data. It strongly implies it supersedes the per-field validators but never names them or states an explicit when-not (e.g. 'use validate_iban alone if you only want syntax checking'), so it stops short of a 5.

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