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

Annotations already declare readOnly/idempotent/openWorld safety, yet the description adds real behavior: the non-trading-day fallback ('the latest ECB day on or before it, named'), the 1999 historical floor, cross-rate derivation through the euro, and Decimal precision with minor-unit rounding. It does not mention failure behavior for unknown currency codes, which is the main remaining gap.

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 tightly packed sentence with the resource and coverage window front-loaded and the dealing-rate caveat last. The stacked parentheticals ('the latest ECB day on or before it, named') make it denser than necessary but nothing is filler.

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 must imply the return shape, and it does via 'Decimal' and 'named' (the effective rate date comes back). For a four-parameter read tool this covers what an agent needs to call it correctly; only error cases and default base/quote behavior are left implicit.

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 description), so the description has to compensate, and it does: it establishes base/quote as currency pairs with cross-rate support through the euro, and explains that amount is converted and rounded to the quote currency's minor units. It never states the length-3 ISO-code constraint or the USD/EUR defaults explicitly, which is why it is not a 5.

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 resource and scope: 'ECB euro reference rate for any pair on any date since 1999', plus cross-rate and amount conversion behavior. The closing caveat 'Reference rate, not a dealing rate' disambiguates what kind of rate is returned, and no sibling tool (business_days, vat_check, etc.) overlaps with FX, so differentiation is unnecessary.

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 the use case clearly (retrieve an official reference rate for a currency pair, optionally converted), and the 'not a dealing rate' line is an explicit exclusion telling agents not to use it for tradeable quotes. It does not state exclusions for unsupported currencies or non-ECB-covered pairs, nor alternatives for a market-quote rate, so it stops short of full when/when-not guidance.

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