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

With no annotations, the description carries the full load and does so well: it discloses non-obvious behavior — weekend/holiday requests fall back to the most recent prior publication, and effectiveDate reports the date actually used. The historical boundary (data starts 2013-01-02) is another useful disclosure. It is silent on caching behavior and error/empty-result handling, which keeps it off a 5.

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?

Dense and front-loaded — scope and unit come first, modes second, edge behavior third. Minor redundancy between 'Published every business day' and 'NBP publishes only on Polish business days', which say nearly the same thing twice.

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?

No output schema and no annotations, and the description does name at least one response field (effectiveDate) plus the date floor, which covers the main ambiguity. It stops short of indicating the return shape for the single-value versus list modes, leaving some guesswork about whether last_n/range return an array.

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, but the description adds genuinely schema-adjacent meaning: no parameters yields the latest price by default, and the modes are mutually exclusive alternatives rather than combinable filters. The remaining limits (255, 93 days) merely restate schema text.

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?

Names a specific resource and unit (official NBP gold price, PLN per 1 gram of 1000-fineness gold), which immediately distinguishes it from the currency-focused siblings (nbp_convert, nbp_exchange_rate, nbp_rate_series). The four supported query modes are stated in the same breath as the purpose.

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?

Enumerates the four calling modes (default latest, single date, last_n, start/end range) with their caps (255 quotes, 93-day span), so mode selection is clear. It does not explicitly say when to prefer a sibling such as nbp_rate_series, though the gold-only scope makes that largely self-evident.

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