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 context: a per-call cost of 1 credit and the JSON shape returned by each operation. It stops short of stating rate limits, throttling, or data freshness beyond 'latest'.

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?

Two sentences plus a compact per-operation output spec, with purpose, cost, and return shapes front-loaded and nothing redundant. Every clause carries information an agent needs before calling.

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 usefully enumerates the three return shapes, and it flags the credit cost. For a 9-parameter, zero-required tool it leaves defaults and the 'quotes' batching behavior to the schema, which is acceptable given the 89% coverage.

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 already 89%, so baseline is 3, but the output shapes ('base, quote' for history; 'amount, from, to' for convert) implicitly map parameters to the operation that consumes them, clarifying that some fields are op-specific aliases. This adds meaning beyond the per-property descriptions without fully explaining defaults.

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+resource ('euro foreign exchange reference rates from the European Central Bank') and adds the conversion capability, which is a distinct function. No sibling tool touches currency, so an agent can identify it immediately among the many conversion/format siblings.

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 three modes (latest, convert, history) are named along with their outputs, which implies when each applies, but there is no explicit when-to-use guidance or exclusions. Since no sibling overlaps, the practical risk is low, so this is adequate rather than strong.

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