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

With annotations already covering readOnly/openWorld/idempotent, the description still adds substantial operational context: publication cadence (~16:00 CET on working days), freshness via the included rate date, and the paid x402 USDC-on-Base model with cost and the PaymentRequired response when unpaid. This is exactly the kind of detail annotations cannot carry.

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 'Use when...' and every sentence carries either scope, freshness, or payment information. It is dense but not padded; only the enumeration of use cases is slightly redundant.

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 still tells the agent what comes back (rates plus the rate date for freshness) and how payment works. Nothing needed to call it correctly appears missing.

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 100%, so both parameters are already documented, establishing a baseline of 3. The description adds mild meaning ('re-based to any supported currency', 'all ~30 if omitted') but no format or syntax 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: returns latest ECB reference rates, re-based to a chosen base and optionally filtered by symbols. It also implicitly separates itself from fx_history (latest vs historical) and fx_convert (rates vs conversion), so an agent can route without opening the 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?

Gives clear when-to-use ('current, citable exchange rate') and when-not ('Not for trading; for pricing, reporting, invoicing'), which is solid context. It does not name a sibling alternative (e.g. fx_history for past dates) explicitly, keeping it short of a 5.

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