Look up the applicable VAT rate for a country (and optional rate type), sourced from the EU TEDB (Taxes in Europe Database).
| Name | Required | Description | Default |
|---|---|---|---|
| country | Yes | ISO-2 country code | |
| rate_type | No | Defaults to 'standard' if omitted |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so description carries the burden. It discloses the data source (EU TEDB) which adds trust/context, but doesn't say whether the lookup hits a live API, returns cached data, or what happens for unsupported countries. Mutating or read-only is implied (lookup is read) but not explicit.
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?
One clear sentence, properly front-loaded with the action and resource. No waste, though it could mention the default rate type explicitly in text to reinforce the schema.
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?
A simple two-parameter lookup with a well-documented schema. The description plus schema covers core usage; no output schema means return format isn't promised, but for a rate lookup it's likely a numeric rate. Missing minor context like coverage scope (EU only?) and response shape, but adequate for basic use.
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 covers 100% of parameters with descriptions (ISO-2 code and enum). Description adds source context but no additional parameter details beyond 'optional rate type'. Baseline 3 is appropriate since schema already explains the parameters well.
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?
Clear verb+resource: 'look up the applicable VAT rate for a country' with optional rate type. It distinguishes itself from a generic lookup by naming the EU TEDB source, but doesn't name any sibling alternatives.
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?
Implied usage: a lookup tool for VAT rates, with rate_type defaulting to standard. No explicit when/how to choose this over other tools, and no exclusions or context about when it applies (e.g., EU vs non-EU).
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 has a distinct primary purpose: registration, validation, rate lookup, reverse-charge certification, and full compliance analysis. There is slight overlap because reverse_charge_certificate also validates VAT IDs via VIES, but the descriptions clearly differentiate the outputs and use cases.
Most tools follow a descriptive snake_case pattern with a vat_ prefix, such as vat_number_check and vat_registration_check. reverse_charge_certificate and vat_compliance_full deviate slightly from the prefix/pattern but remain consistently readable.
Five tools is a well-scoped size for a VAT compliance server. Each tool covers a distinct compliance need without unnecessary redundancy or bloat.
The set covers the core VAT compliance workflow: registration eligibility, VAT number validation, rate lookup, reverse-charge eligibility, and a broad gap analysis. Some edge cases like reverse charge for goods or detailed place-of-supply rules are not explicitly covered, but the core domain is well served.
