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

Annotations already mark it read-only, idempotent, and non-destructive, and the description adds high-value behavior beyond those flags: VIES unreachability is reported as `unknown`, PDFs/scans are refused rather than interpreted, and the tool returns findings with fixes plus draft e-mail and XML export. No contradiction with 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?

Purpose is front-loaded, followed by checks, outputs, then constraints. Each sentence carries distinct information and none is 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?

For a complex 9-parameter tool with nested objects and no output schema, the description covers inputs, processing, outputs, constraints, and edge-case behavior. An agent has enough context to call it correctly and interpret its result.

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 the baseline is 3; the description adds meaning by explaining how line items (totals recomputed) and supplier/customer vatId values (checked against VIES) are used and validated. It does not explain every parameter, but the schema already does that.

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 precise action and object: 'Review one structured invoice end to end and say whether it can be sent as an e-invoice.' It enumerates specific checks (Peppol field contract, line/document totals, VIES VAT verification, UBL 2.1/Peppol BIS Billing 3.0 build), which separates it from siblings like format_peppol_invoice or check_peppol_ready.

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?

It gives clear when-not guidance: structured invoice data only, no OCR, so PDFs and scans are refused; and read-only, so it never sends or signs. It stops short of naming sibling tools to route to alternative workflows, so it lacks fully explicit alternatives.

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