BNR rates: several currencies, or a window

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

Annotations already declare readOnly/idempotent/openWorld, and the description adds substantive behavior beyond them: fallback to the last banking day's fixing when the day has none, oldest-first ordering, hard limits of 366 days and 2000 rates per call, and per-series multipliers. These are exactly the traits an agent needs to size requests and interpret values.

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 sentences, front-loaded with what the tool returns, then mode behavior, then coverage and limits. The parentheticals carry real information (defaults, multiplier rule) rather than restating the schema — every clause 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?

With an output schema present, return-format detail is unnecessary, and the description covers the remaining risk areas: input mode exclusivity, defaults, request caps, and the meaning of the multiplier. Little an agent needs to call this correctly is missing.

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%, so the baseline is 3; the description earns above that by adding semantics the schema lacks — that `to` is inclusive and defaults to today, that `date` is in Bucharest time, that result rates reflect non-banking-day fallback, and that omitting `currencies` returns everything BNR published.

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?

States a specific verb+resource: BNR reference rates returned as series in the exact published text, with two modes (single day vs. window). It is distinguishable from `annual_average` and `convert`, though it never explicitly names the `rate` sibling, leaving the single-rate-vs-series boundary to be inferred from the title.

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?

Gives clear mode-selection guidance: use `date` for one day's rates in force, use `from`/`to` for a window of fixings. It stops short of explicit exclusions or routing to siblings such as `rate` or `convert`, so the agent must infer which tool to pick for a single conversion.

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