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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: it discloses the two operation modes, the exact standards targeted (EN 16931, Peppol BIS 3.0, UBL 2.1, XRechnung) and the concrete endpoint. It stops short of describing error behavior for malformed XML or missing BIC.

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?

One dense sentence plus an endpoint line, with the resource and standards front-loaded. Slight redundancy between the lead phrase and the title annotation, but no filler or repetition that would waste an agent's attention.

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 carries the burden of describing return values; it only gestures at outputs ('XML and SEPA EPC-QR payloads', 'UBL XML to JSON') without indicating response shape or how both artifacts are returned together. The nested 'invoice' object is left entirely opaque, which is the largest gap for a converter of this complexity.

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 nominally documents all three parameters, which sets the baseline at 3. The description adds no parameter-level detail — notably nothing about the required nested 'invoice' object's expected fields or the role of seller_bic in EPC-QR generation — so it neither compensates nor detracts.

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 names specific verbs and artifacts: generate EN 16931 / Peppol BIS 3.0 UBL 2.1 XML and SEPA EPC-QR payloads from JSON, or parse UBL XML to JSON. That is far more than a restatement of the name and makes the tool's function unambiguous. It does not, however, distinguish itself from the sibling tinplate_invoice_validator (generate vs. validate), so an agent must infer that boundary.

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 phrase 'from JSON, or parse UBL XML to JSON' implies the two operating directions, giving some usage signal. But there is no explicit statement of when to choose generation versus parsing, no prerequisites (e.g. that seller_bic is needed for SEPA QR output), and no routing to the invoice validator sibling.

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