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

With no annotations provided, the description carries the full burden and succeeds: it reveals dual data sources (ECB and market), the meaning of the 'source' and 'source_note' fields, cross-rate computation via EUR, possible missing currencies, and exact error behavior. This goes well beyond basic 'get rate' and covers important caveats the agent must know.

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?

Although long, the description is tightly structured with clear paragraphs: first the rate definition and source caveats, then cross-rate explanation, then requirements, then arguments and examples. Each sentence adds non-redundant information; the length is justified by the tool's behavioral nuances. Front-loaded with the main verb phrase.

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 is complete for a 2-parameter tool with an output schema. It covers provenance, edge cases (missing currencies), calculation methodology, error semantics, and argument requirements. Given the output schema exists, the description need not list return fields, but it already explains the key 'source' and 'source_note' fields. No significant gaps remain.

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?

The input schema only defines 'base' and 'target' as strings with no enum or description. The description compensates fully: explains they are ISO 4217 currencies, both are always required, gives multiple usage examples, and clarifies that omitting or mis-naming a currency returns an error. It also resolves ambiguity around ordering (e.g., USD/VND vs EUR/USD).

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 opens with a specific verb+resource: 'Get the latest available reference (mid-market) exchange rate for a pair.' It distinguishes from siblings like fx_rate_history (history vs current), and adds useful qualifiers (reference, mid-market, latest). The examples make clear the tool returns a single rate for an exact pair.

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 extensive when-to-use details: check the 'source' field, never call market rates 'ECB rate', both currencies are required, no implicit default pair, and what to do when a currency is missing. However, it does not explicitly reference alternative sibling tools (e.g., fx_rate_history, fx_timing_advisor) or state when NOT to use this tool in favor of another, so it misses the 'alternatives' criterion for a 5.

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