exchange_rates_list

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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint, yet the description adds real value: daily refresh around 13:00 EET and fallback to the last available rates on weekends and holidays. What remains unstated is pagination or a currency subset filter, though it says all supported currencies are returned, which pre-empts that question.

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?

Three short sentences, front-loaded with the purpose, then update cadence, then return format and edge-case behavior. No sentence is filler.

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?

With no output schema, the description carries the burden of describing the return, and it does so by specifying the currency direction and the all-currencies scope. The only residual gap is that the schema's date parameter implies historical lookups the description never acknowledges.

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 single `date` parameter is fully documented in the schema (including the default to latest available), so the baseline 3 applies. The description's framing around "current" rates adds nuance but does not explain how the date parameter yields historical rates.

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?

Specific verb+resource ("Get current BNR exchange rates"), names the authoritative source and states the return semantics ("1 foreign currency = X RON"). It does not explicitly differentiate from the sibling exchange_rates_convert, so an agent must infer that this lists rates while that one performs a conversion.

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?

Usage context is implied by the weekend/holiday staleness note, which tells the agent the tool still returns data on non-business days. However, there is no explicit statement of when to prefer this over exchange_rates_convert or what to do with the returned rates.

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