render_invoice_pdfHuman-readable PDF of the invoice (counts as 2 requests). Returned as a base64 resource.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | ||
| content | No | Invoice XML (UBL, CII, XRechnung, Peppol BIS, ZUGFeRD/Factur-X XML, KSeF FA(3)) as text | |
| content_base64 | No | A ZUGFeRD / Factur-X PDF (or any invoice file) as base64, when the invoice is not plain XML |
Changes observed during successful MCP inspections.
Input schema / properties / lang / enumPrevious value: -[
- "en",
- "de",
- "fr",
- "pl",
- "nl",
- "hr"
-]New value: +[
+ "en",
+ "de",
+ "fr",
+ "pl",
+ "nl",
+ "hr",
+ "es"
+]Input schema / properties / lang / enumPrevious value: -[
- "en",
- "de",
- "fr",
- "pl",
- "nl"
-]New value: +[
+ "en",
+ "de",
+ "fr",
+ "pl",
+ "nl",
+ "hr"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses two non-obvious traits: the call costs 2 requests (a quota/rate signal) and the result is returned as a base64 resource rather than a URL or inline text. It does not say which input parameter must be supplied, how errors surface, or what happens when neither content nor content_base64 is given.
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?
Two short sentences, zero filler, with the output format and the cost caveat front-loaded. Every clause carries information an agent needs.
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?
The description covers the return channel (base64 resource) and the cost, which is what matters most with no output schema and no annotations. However, it omits input selection (content vs content_base64, mutual exclusivity) and the meaning of lang, leaving gaps for a 3-parameter conversion tool.
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 67%, with content and content_base64 well documented in the schema but lang carrying only an enum and no explanation. The description adds nothing about parameter usage, so it neither compensates for the lang gap nor improves on what the schema already provides.
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 the output artifact precisely (a human-readable PDF of the invoice) and the sibling set makes the implied verb (render) obvious. It implicitly distinguishes itself from render_invoice_html by producing PDF rather than HTML, though it never names that sibling explicitly.
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?
There is no explicit when-to-use guidance or routing between this tool and render_invoice_html. The agent must infer that this is the choice when a PDF is wanted rather than an HTML view; no conditions, prerequisites, or exclusions are stated.
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.