FX conversion (ECB) — $0.005 per call (x402, USDC on Base). Currency conversion using ECB euro reference rates. Informational only — not tradeable quotes.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | ISO 4217 code, default USD. | |
| from | No | ISO 4217 code, default EUR. | |
| amount | No | Amount to convert, default 1. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the cost per call ($0.005), payment rail (x402, USDC on Base), data source (ECB euro reference rates), and the non-tradeable nature of the quotes. This goes beyond a basic function statement and provides useful operational context, though it doesn't mention rate limits or error behavior.
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 two sentences, front-loaded with the core purpose ('FX conversion (ECB)') and then succinctly adds cost, payment method, source, and caveat. No unnecessary words; every sentence earns its place.
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?
For a simple conversion tool with three optional parameters and no output schema, the description covers the essential context: purpose, cost, payment rail, data source, and informational nature. The return format is implied but not explicitly stated, which is a minor gap. Overall, it's sufficiently complete for an agent to invoke correctly.
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?
The schema covers all three parameters (from, to, amount) with descriptions and defaults (EUR, USD, 1 respectively). The description adds the rate-source context but no additional parameter-specific meaning. Since schema coverage is 100%, the baseline of 3 is appropriate.
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 tool performs FX conversion using ECB euro reference rates, with a specific verb and resource. It also distinguishes itself from tradeable quote services by stating 'Informational only — not tradeable quotes.' This makes the purpose unambiguous and distinct from sibling tools.
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 explicitly indicates the tool is for informational conversions and not for tradeable quotes, providing a clear context for when to use it (and when not to). It also mentions the cost and payment method, which helps an agent decide if it's appropriate. However, it doesn't name alternative tools, leaving a slight gap in direct alternatives.
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 targets a distinct data source or function: address lookup, building info, demographics, elevation, school holidays, vehicle lookup, validation, currency conversion, plus meta-tools for catalog and sample responses. There is no meaningful overlap between any pair of tools.
The Dutch-specific tools all follow a consistent 'nl_<subject>' pattern (nl_address, nl_building, etc.), and all names use snake_case. However, three tools (catalog, global_fx, sample) break the prefix pattern, creating a minor inconsistency but remaining clear and readable.
With 11 tools, the server is well-scoped for a Dutch open data API. Each tool covers a distinct data domain, and the count is within the ideal range without feeling excessive or sparse.
The tool surface covers a broad range of Dutch open data lookups, including addresses, buildings, demographics, elevation, holidays, and vehicles, along with validation and a sample mechanism. Minor gaps exist (e.g., no weather or property value data), but the core domain is well represented.