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

With no annotations, the description carries the full burden of disclosing behavior. It clearly states the tool retrieves data (implying read-only), supports live/historical rates, is ECB-sourced, and explicitly excludes cryptocurrency pairs. It also notes a fallback source ('Frankfurter is unavailable'), which adds context. However, it does not mention rate limits, error behavior, or response format, so it is not maximally transparent.

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?

The description is longer than ideal but every sentence earns its place by providing essential guidance on when to choose this tool over alternatives. It is front-loaded with the core functionality, and the additional sentences are structured as clear comparisons. It is concise for the amount of useful information delivered.

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?

The description thoroughly addresses the tool's purpose and sibling differentiation, but it omits a critical detail: the schema does not include a date parameter, yet the description heavily promotes historical lookup. This gap undermines completeness for an agent trying to use the tool correctly. Additionally, with no annotations or output schema, the description should clarify return behavior and any limitations, which it does not.

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?

While the schema has 100% coverage for the three parameters (amount, from, to), the description introduces a significant mismatch by claiming support for 'historical rate lookup for any past date' without including a date parameter in the schema. This could mislead an agent into attempting to pass a non-existent date parameter. The description adds no value beyond the schema for the actual parameters and actively creates confusion, so it falls below the baseline.

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?

The description uses a specific verb ('Retrieves') and clearly identifies the resource ('fiat currency exchange rates') and source ('Frankfurter API, sourced from the European Central Bank'). It explicitly distinguishes from siblings by highlighting historical lookup and ECB sourcing, making the tool's unique role 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?

The description provides explicit when-to-use guidance ('Use currency_rates when a rate from a specific past date is required... or when the ECB source must be documented') and names specific alternatives with their appropriate contexts (currency_convert, currency_convert_lite, currency_fx_lite, currency_convert_open, crypto_fx_rates). This exceeds the typical level of usage direction.

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