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

Annotations only declare readOnlyHint and openWorldHint; the description goes well beyond by disclosing the commercial model ($0.001 USDC fixed per request), the charge semantics (one paid HTTP GET = one charge, x402 on Base vs MPP on Tempo), and crucially that 4xx errors are not charged — a behavioral detail an agent needs to plan retries. It also states the returned fields (as_of date, source attribution).

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 core scope and results before the commercial detail; the example currency list and pricing clause are dense but each carries decision-relevant information. Slightly overpacked into one flowing block, but no dead sentences.

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?

No output schema exists, yet the description covers the return payload (as_of date, source attribution), so an agent knows what comes back. Coverage of cost and error-charging makes it strong; the only gap is failure behavior for an invalid currency code, which is minor for a two-optional-param read tool.

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 description coverage is 100% and both parameters already carry defaults and meaning (base default EUR, symbols default all). The description adds only a marginal gloss — 'in any base currency' and 'filter with symbols' — without new syntax detail (e.g. whether symbols overrides base or which ~30 codes exist). Baseline 3 for a schema-documented parameter set.

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+scope: 'Today's exchange rates (forex reference rates, most recent ECB publication) for ~30 currencies in any base currency.' The 'today / most recent' framing cleanly separates it from siblings rates_historical and rates_timeseries, and the concrete example pairs (USD to JPY, CNY, EUR...) make the domain unambiguous.

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?

Usage is implied through 'Filter with symbols' and the example pairs, but there is no explicit routing advice: nothing says to use rates_historical for past dates, rates_timeseries for a range, or convert for cross-rate arithmetic. For a family with three closely related rates/convert tools, the exclusions are left to inference.

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