Официальные курсы валют ЦБ РФ

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered, and the description's 'Только чтение, без токена' merely corroborates it. The real added value is disclosing the holiday fallback: if no rate was set, the Central Bank returns the last effective one and the date field reveals which date it belongs to — a non-obvious trait not present in the structured data.

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 but efficient: purpose, default, filter, and fallback behavior are front-loaded with no filler. It is a single packed paragraph rather than cleanly segmented points, which slightly hurts scanability but not content economy.

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 compensates by describing the return shape (rubles per unit and per nominal, date field indicating effective date) and the fallback semantics. Both optional params are understood, so an agent has enough to call it correctly, though explicit sibling routing would complete the picture.

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 description coverage is 100%, so both parameters (date format, ISO codes with example) are already fully documented in the schema, making 3 the baseline. The description reinforces the codes filter and date default but adds no syntax or format detail beyond what the schema states.

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 ('Официальные курсы ЦБ РФ на дату') and pins the exact output semantic — rubles per unit of currency and per nominal. This is clearly a single-date rate lookup, distinguishable from siblings like cbr_rate_history (time series) and currency_convert (conversion) without opening either schema.

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?

Implies usage through defaults ('по умолчанию на сегодня') and the optional code filter, which tells an agent how to scope the call. However, it never names alternatives or when-not-to-use conditions — e.g. that cbr_rate_history should be preferred for ranges — so routing is left to inference.

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