Your existing PDF invoice + invoice JSON → Factur-X / ZUGFeRD PDF/A-3 with embedded XML (1 credit).
pdf_base64: the original PDF, base64-encoded (max 15 MB). Returns {pdf_base64, cert_id, verify_url,
credits_left}. The output is validated (EN 16931 + PDF/A-3) before delivery; failures are not charged.| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | ||
| invoice | Yes | ||
| pdf_base64 | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full disclosure burden and does it well: it mentions the 1-credit cost, the 15 MB input limit, validation against EN 16931 and PDF/A-3, and that failures are not charged. It does not discuss auth or side effects beyond creation, but this is acceptable for a creation 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?
The description is compact, front-loaded with the core transformation, and efficiently covers cost, size limits, output fields, validation, and failure policy. Every sentence adds useful information.
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?
It names output fields and critical constraints, which is helpful given the lack of an output schema. However, the invoice JSON structure is not explained, and without it an agent may not be able to construct valid input reliably.
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 0%, so the description must compensate. It explains pdf_base64 (base64-encoded, max 15 MB) but leaves the invoice object's required structure and fields undocumented. The api_key parameter is also not described, leaving significant gaps for the required parameters.
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 a specific operation and resource: converting an existing PDF invoice plus invoice JSON into a Factur-X/ZUGFeRD PDF/A-3 with embedded XML. This clearly differentiates it from siblings like generate_einvoice_xml and validate_einvoice.
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 states clear input prerequisites: an existing PDF invoice and invoice JSON. It also implies the intended use case by describing the output format, though it does not explicitly mention when to prefer an alternative such as generate_einvoice_xml.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool covers a distinct operation: credits, signup, format advice, XML generation, PDF/Factur-X generation, validation, and certificate lookup. Even generate_einvoice_xml and create_facturx_pdf are clearly differentiated by output format, so an agent should not misselect.
Most tools follow a lowercase snake_case verb_noun pattern like check_credits, generate_einvoice_xml, and validate_einvoice. The exceptions are signup (no underscore) and which_format_do_i_need (question-style phrase), which present minor but noticeable deviations.
Seven tools is well-scoped for an e-invoice API: each covers a meaningful step in the user journey from signup and credit checking to format selection, generation, validation, and verification. No tool feels redundant or unnecessary.
The tool set provides a coherent end-to-end workflow: onboard with signup, check credits, determine the required format, generate XML or create a Factur-X PDF, validate the result, and look up verification certificates. There are no obvious dead ends for an agent attempting to produce and verify an e-invoice.