Skip to main content
Glama

Check a Dutch SI-UBL 2.0 / NLCIUS invoice (free)

check_si_ubl
Read-onlyIdempotent

Free, no sign-in needed: check a Dutch e-invoice — SI-UBL 2.0 (NLCIUS, the Dutch government and SimplerInvoicing standard), NLCIUS CII or Peppol BIS Billing 3.0 from a Dutch supplier — against 31 SI-UBL 2.0 / NLCIUS rules (BR-NL-), Peppol's 9 Netherlands rules (NL-R-) and 189 EN 16931 rules. Returns pass/fail with rule IDs, line numbers and plain-language fixes; KvK/OIN, address, buyer-reference and payment-means problems are named explicitly. Not the official validator (no XML Schema check, not every EN 16931 rule); for a final check: https://test.peppolautoriteit.nl/validate. The invoice is not stored. Shares the 20 free calls per hour per connection with the other free tools (check_peppol_receivability, search_peppol_directory, check_factur_x and check_si_ubl).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "xml": "<xml>"
    },
    "name": "check_si_ubl"
  }
}

Input Schema

NameRequiredDescriptionDefault
xmlYesThe complete invoice XML (UBL Invoice / CreditNote or CII).
filenameNoOriginal file name, shown in the report.
force_si_ublNoApply the SI-UBL 2.0 rules even if the CustomizationID doesn't say SI-UBL 2.0 (default false: detect it).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent and closed-world, and the description goes well beyond them: it discloses the rate limit (20 calls/hour per connection, shared across four named tools), a privacy guarantee (invoice not stored), and honesty about coverage gaps versus the official validator. It also describes the shape of the result (pass/fail with rule IDs, line numbers, plain-language fixes, named KvK/OIN, address, buyer-reference and payment-means issues).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the strongest qualifiers (free, no sign-in) and then ordered by what/limits/caveats/rate limit. It is a single dense run-on paragraph, and the list of sibling tools inside the rate-limit sentence could be trimmed, but every sentence carries usable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a stateless validator with no output schema, the definition supplies everything an agent needs: accepted input formats, rule-set coverage and its limits, result contents, privacy behavior, rate limits and a fallback for authoritative validation. Nothing material is left to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains xml, filename and force_si_ubl, including the CustomizationID detection behavior. The description adds nothing parameter-specific beyond noting the accepted formats (UBL Invoice/CreditNote or CII) and the Dutch-supplier scope. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (check) and resource (Dutch e-invoice in SI-UBL 2.0 / NLCIUS / CII / Peppol BIS 3.0) and quantifies exactly what is evaluated (31 BR-NL rules, 9 NL-R rules, 189 EN 16931 rules). It also declares what the tool is not (not the official validator, no XML Schema check), so an agent can separate it from sibling checkers without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear triggering context (Dutch supplier e-invoice) plus an explicit escalation path to the official validator for a final check, which doubles as a when-not-to-rely-on-this-tool signal. It stops short of directly routing to sibling tools such as check_factur_x for non-Dutch formats; the sibling list appears only in the shared rate-limit sentence, not as an alternative-selection rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources