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

Annotations already declare read-only, idempotent, non-destructive, open-world behavior, and the description adds substantial context beyond them: upstream source (Frankfurter/ECB reference rates), update cadence (~16:00 CET working days), coverage window (since 1999), cost (free), and error semantics (isError with message for invalid input or upstream failure, not charged). This is exactly the behavioral disclosure the annotations cannot convey.

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-loads the core purpose, then source/cadence, then the sibling redirect, then cost and error behavior. Every clause carries information (coverage window, cadence, cost, error handling) with no filler or repetition.

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 an output schema present, return-value shape need not be explained. The description covers source, cadence, coverage window, modes, cost, error behavior, and the crypto alternative — everything an agent needs to invoke it correctly and interpret failures.

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 the baseline is 3; the description goes further by framing parameter combinations as modes (latest vs. any date since 1999 vs. amount conversion vs. time series), which clarifies how date/end_date/amount interact. It adds mode-level meaning but no per-parameter format detail beyond the schema.

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 the resource (official ECB reference exchange rates for 30 major currencies) and the concrete verbs/modes (latest, historical date since 1999, amount conversion, time series). It explicitly distinguishes itself from the crypto sibling by naming crypto_price, so an agent can select it 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 one explicit exclusion and redirect: 'For crypto use crypto_price.' Provides data-source and freshness context (published each working day ~16:00 CET) that helps the agent decide relevance, but offers no guidance on the modes' relative use or when not to call it beyond the crypto case.

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