Get a bank's official published rates

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

Annotations already mark readOnly and openWorld, and the description adds behavior beyond that: weekend/holiday rollback to the last published date, a derived flag when cross-computed, paid-plan gating for date, and the response's rate_date field. This gives the agent operational knowledge not inferable from annotations.

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?

Four dense sentences, front-loaded with the purpose and followed by examples, parameter semantics, and an alternative. No filler or redundancy; each sentence adds a distinct operational fact.

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 tool with no output schema, the description covers the return shapes ({rates:[...]} and derived flags), edge cases (weekends/holidays, paid plans), input selection, and the alternative for live rates. Sibling tools are not explicitly routed, but the scope is defined clearly enough that history/comparison/calendar tools are not confused with this point-in-time official rate lookup.

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?

With 100% schema coverage, the baseline is 3, but the description meaningfully enriches each parameter: bank codes are lowercase abbreviations (call list_central_banks first), date is optional and requires a paid plan for specific days, and source/target must be given together to narrow to one pair. It also explains output shape implications, which the schema does not.

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 leads with a specific verb and resource: getting official published rates from a specific institution. Concrete examples ('ECB rate for USD', 'HMRC rate for invoicing') and the explicit contrast with live market rates make the tool's purpose unmistakable and distinguish it from other rate-related 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?

Explicitly says when to use this tool ('Use this for OFFICIAL rates...') and when not ('NOT live market rates'), and names the alternative package for live mid-market rates. It also gives parameter-based guidance: omit date for latest, supply date for a specific table, omit source/target for full table, provide both for one pair.

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