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

With no annotations, the description carries the burden and does it well: it discloses the weekend/holiday fallback to the last preceding publication, that effectiveDate in the response shows the date actually used, and that table 'c' returns bid/ask rather than a mid rate. It does not discuss caching behavior beyond what the schema's no_cache field implies, but the key gotcha for an agent (silent date fallback) is surfaced.

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 compact sentences, front-loaded with the core action and default, then table semantics, then the fallback caveat, then the alternative tool. No filler and nothing buried.

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 exists, yet the description names a return field (effectiveDate) and its meaning, which is exactly the gap that would otherwise hurt. The only shortfall is the lack of differentiation from the other rate-related siblings (nbp_convert, nbp_exchange_rates).

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 baseline is 3, but the description adds behavior the schema does not: that 'date' is the rate 'in force on' that day rather than a strict publication date, and the mid-vs-bid/ask consequence of the table choice. That is meaningful semantics beyond the enum and pattern already documented.

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 and resource ('Get the official NBP rate for one currency against PLN') and immediately scopes the two modes: latest by default or a historical date. It also names the sibling it is not (nbp_rate_series) for multi-day history, so an agent can route without opening schemas.

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 routes multi-day history to nbp_rate_series and explains the latest-vs-historical selection via the date parameter. It does not distinguish itself from nbp_convert or nbp_exchange_rates (plural), which remain plausible alternatives for a converting or bulk-rates use case.

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