parse_ubl_invoice_be

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

With no annotations, the description carries the full disclosure burden. It details the accepted formats, extracted fields, and exact success/error return shapes. It omits side-effect information, but parsing is inherently read-only, and the behavioral disclosure is sufficient for an agent to understand the tool's operation and error handling.

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 relatively concise, front-loading the core purpose in the first sentence. It avoids fluff but could be slightly tightened (e.g., the accepted formats are mentioned twice). Overall, it efficiently conveys the necessary information without extra verbiage.

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 a single parameter with full schema coverage and an output schema (assumed from context), the description covers the tool's function, input constraints, and return structure on both success and failure. It does not mention dependencies or prerequisites, but for a parse tool with no nested objects or complex parameters, this is sufficient.

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 provides 100% coverage with a description for 'xml_content' as 'Raw UBL 2.1 XML invoice content (Peppol BIS 3.0)'. The description adds value by specifying that EU PINT v1.0.1 is also accepted, clarifying the parameter's scope beyond the schema. This extra context merits a score above the baseline 3.

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 parses UBL 2.1 XML invoices into a structured dict, specific to Peppol BIS 3.0 or EU PINT v1.0.1 documents, and extracts EN 16931 fields plus Belgian extensions. This is a distinct task from siblings like validate_invoice_be (validation) or transform_to_ubl (transformation).

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 specifies the input document types (Peppol BIS 3.0, EU PINT v1.0.1) and explains the return format, helping an agent decide when to invoke the tool. However, it does not explicitly contrast with siblings or state when not to use it, leaving some ambiguity about alternatives like validation or transformation.

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