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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds one genuinely useful behavioral constraint not in any structured field: the 366-day window ceiling. It says nothing about gaps for weekends/holidays, date ordering requirements, or what the returned series looks like.

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?

A single front-loaded sentence with no filler; the range limit is packed into the same clause rather than padding the definition. Nothing is redundant with the title or annotations.

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?

For a read-only, three-parameter tool with no output schema, the description covers what the tool retrieves and its window limit, which is close to sufficient. It still leaves the response shape (date/rate pairs, ordering) and currency-code conventions unexplained, which an agent would need to use results confidently.

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?

At 67% schema coverage, end and start are documented in the schema but currency has no description beyond a default of USD. The description implies currency is an ISO-style code input and adds the 366-day range limit that applies to start/end, which is real value, but it doesn't clarify the currency format or behaviour on unsupported currencies.

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 Bank Indonesia exchange rate history') plus the scoping dimension ('over a date range'), which is clearly distinct from a latest-rate tool. However, it never explicitly contrasts itself with the sibling kurs_history, so the agent must infer that this one is BI-sourced specifically.

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?

The 'max 366 days' note implies the intended use (bounded historical lookups) but there is no explicit when-to-use/when-not guidance and no pointer to kurs_bi_latest for current rates or kurs_history for the other source. The selection logic between the three kurs tools 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.