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 genuinely new behavior: date snapping to the latest ECB publishing day, cross-rate derivation through the euro for non-EUR pairs, Decimal precision, and rounding of optional amount to the currency's minor units. It stops short of describing the exact response shape, which matters since no output schema exists.

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?

Front-loaded with the resource and source (ECB euro reference rate), then bounded with scope ('any pair on any date since 1999'). It is one heavily parenthesized sentence, which is dense but nearly every clause carries distinct information; the trailing caveat is short and high-value.

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, open-world lookup with no output schema, the description covers source, coverage window, date-fallback semantics, cross-rate mechanics, numeric precision and rounding. The one meaningful omission is the shape of the return value, which the description hints at ('in Decimal', 'named') but never states explicitly.

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 only 50% (base and quote carry no descriptions), so the description must compensate, and it does: it explains that arbitrary pairs are handled as cross rates through the euro, that amount is expressed in the base currency, and that the result is rounded to the quote currency's minor units. It omits the base=USD/quote=EUR defaults and the base-to-quote direction of conversion, which are the remaining gaps.

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 combination: it returns the ECB euro reference rate for any currency pair on any date back to 1999. It also pins the precise object returned ('reference rate, not a dealing rate'), so an agent cannot confuse it with a dealing/spot quote. Siblings are unrelated domains, so no sibling disambiguation is needed.

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 closing clause 'Reference rate, not a dealing rate' is an explicit when-not-to-use constraint that tells an agent this is unsuitable for transaction pricing. It also establishes the date-fallback rule (latest ECB day on or before the requested date) so the caller knows the result may not match the exact date. It does not name any alternative tool, but none exists in the sibling set.

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