get_currencyReturn the ISO 4217 record for a currency: its code, name, symbol, how many decimal places it uses, and every country that uses it.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | ISO 4217 currency code, e.g. NGN, KES, XAF, ZAR. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavior. It does list the return fields, which is helpful, but it fails to mention potential error handling for invalid or non-African currency codes, case sensitivity, or whether the 'African' restriction in the title is enforced. This leaves behavioral gaps for the agent.
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 a single, well-structured sentence that front-loads the purpose and concisely lists the return fields. Every word contributes meaning, with no redundant or vague phrasing.
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 one-parameter tool with no output schema, the description provides substantial context by listing the return fields. However, the ambiguity around the 'African currency' restriction and lack of error expectations reduce completeness slightly. Overall, it is adequate for most use cases.
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 parameter description already provides clear examples (NGN, KES, XAF, ZAR). The description adds no additional parameter semantics beyond confirming the input is an ISO 4217 code. Baseline 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 returns the ISO 4217 record for a currency, specifying the exact fields (code, name, symbol, decimal places, countries). It distinguishes itself from sibling tools like get_public_holidays and lookup_bank, which focus on other domains.
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?
While there is no explicit 'when to use' or alternative tool mentioned, the description implies usage for anyone needing ISO 4217 details for a currency. The sibling tools are clearly in different domains, so there is no confusion about when to use this tool. However, it lacks explicit exclusions or alternative suggestions.
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 type: currency, holidays, banks (list vs lookup), phone network, and NUBAN account resolution. Even the two bank tools are clearly separated by purpose—listing all institutions vs resolving one from an identifier. No tool overlaps meaningfully with another.
All tool names follow a uniform verb_noun snake_case pattern (get_, list_, lookup_, resolve_), making the action and resource immediately clear. The convention is applied consistently across all six tools.
With six tools, the server sits comfortably in the ideal 3-15 range. Each tool covers a distinct reference data need without bloat or redundancy, making the count well-scoped for the stated purpose.
The set covers core African financial reference data—currencies, holidays, banks, mobile networks, and NUBAN validation. However, there is no tool to list supported countries or all currencies, which would be a natural complement to the country-based lookups. This is a minor gap that agents can work around.