Read one incoming invoice. Pass a publicly reachable file URL and the country code (de, fr, it, pl, ru, kz, by, us, ae, sa, ua, ge). The API key can be passed once as an X-Api-Key header when the server is added, instead of on every call. Returns a job id and status. Electronic invoices (XML, QR) are free; scans cost 0.07 EUR per page.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | ||
| country | No | de | |
| file_url | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / api_key / defaultAdded value: +""Input schema / requiredPrevious value: -[
- "api_key",
- "file_url"
-]New value: +[
+ "file_url"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and delivers well: it discloses the async return (job id + status), the auth alternative (X-Api-Key header set once at server configuration), the URL reachability requirement, and a pricing model distinguishing free electronic invoices from paid scans. It stops short of failure behavior or rate limits.
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?
Four front-loaded sentences, each carrying distinct payload: purpose, required inputs and country enum, auth shortcut, return value, and cost. No filler or restatement of the name.
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?
No output schema exists, and the description covers the return (job id and status), which is the key missing piece. It does not connect the async job to the sibling get_result or mention polling, leaving a small workflow gap, but is otherwise sufficient for correct invocation.
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, and it largely does: it enumerates the accepted country codes (de, fr, it, pl, ru, kz, by, us, ae, sa, ua, ge), explains the public-URL requirement for file_url, and clarifies api_key can be supplied as a header instead of per call. File format details are only lightly touched.
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 first sentence gives a specific verb and resource ('Read one incoming invoice'), making the operation immediately identifiable. It does not explicitly differentiate from siblings like get_result, though 'Returns a job id and status' hints at the async workflow. Clear but without direct sibling routing.
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 the required inputs ('publicly reachable file URL and the country code') and a valid auth pattern, which implies usage context. However, it never names alternatives or exclusions – it does not tell the agent to poll get_result for the finished output, nor when this tool is the wrong choice.
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.