Check the format of an EU/GB/CH VAT number (syntax only, no VIES registration lookup). Supported country prefixes: AT, BE, BG, CY, CZ, DE, DK, EE, EL, ES, FI, FR, HR, HU, IE, IT, LT, LU, LV, MT, NL, PL, PT, RO, SE, SI, SK, GB, CH.
| Name | Required | Description | Default |
|---|---|---|---|
| vatNumber | Yes | VAT number, e.g. NL123456789B01 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does a good job by disclosing that the check is local syntax-only and does not perform VIES registration lookup. It also lists all supported country prefixes. It does not mention return type or error behavior, but for a simple validation tool this is a minor omission.
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 one clear sentence followed by a necessary list of supported prefixes. There is no redundant wording, and the core purpose and exclusions are front-loaded.
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 the low complexity, a single parameter, and no output schema, the description covers purpose, scope, exclusions, and valid prefixes. It does not explicitly describe the return format, but for a boolean-style validation tool this is a minor gap rather than a blocker.
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 100% and the schema provides an example, so the baseline is 3. The description adds meaningful value beyond the schema by enumerating the supported country prefixes, which clarifies valid input formats. It does not detail per-country rules, but that is not essential for a simple syntax check.
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 specific verb 'Check' and the resource 'EU/GB/CH VAT number', and explicitly delineates the scope as syntax-only, not VIES registration lookup. This makes it easy for an agent to distinguish this tool from related validation or VAT calculation siblings.
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 gives clear context by stating 'syntax only, no VIES registration lookup', telling the agent when this tool is appropriate and when it is not. It does not explicitly name an alternative tool, but the exclusion is specific enough to guide selection.
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.
Most tools have clearly distinct purposes, but some pairs could be confused: html_to_pdf vs url_to_pdf both produce PDFs, read_page vs url_screenshot both fetch a URL, and generate_test_bsn vs generate_brp_test_data both generate Dutch test data. Detailed descriptions mitigate most ambiguity, so agents can usually select correctly.
All tool names follow a consistent snake_case convention with predictable verb_noun patterns (e.g., generate_*, validate_*, memory_*, url_*). The naming is uniform and makes each tool's function easily inferable from its name.
35 tools is a heavy surface for any MCP server, even a general-purpose toolbox. The large number of niche Dutch-specific tools (BRP, UPA, BSN, holidays) may overwhelm agents and increase selection complexity. The server could benefit from splitting into smaller, focused servers.
The server covers a wide range of utilities, but there are notable gaps: no hash generation, no json_to_csv counterpart, and the workflow sub-domain only offers list/run without create/delete. Core utilities are present, but some obvious counterparts and lifecycle operations are missing.