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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond them: no API key required, and an unknown currency yields not_found rather than an error or empty result. Rate freshness/caching is not mentioned, which keeps it short of a 5.

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?

Three compact clauses, front-loaded with the core definition, then behavioral branches, then the auth note. No filler, and every clause carries information an agent needs.

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 must hint at return shape, and it does: an all-rates collection versus a single rate plus a not_found case. It stops short of describing the all-rates structure (e.g., keyed by currency code), a minor residual gap for a one-parameter lookup 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 coverage is 100% (pattern, example, ISO 4217 note), so the baseline is 3. The description goes further by explaining the semantics of omission (returns all rates) and of a non-matching value (not_found), which the schema does not convey.

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 (fiat → USD rates) with directionality, and ties it to the concrete consumer (create_invoice with price_amount + price_currency). No sibling in the list retrieves exchange rates, so the distinction is 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 invoice-pricing context tells the agent when this tool is relevant, and the two modes (omit currency = all rates, supply currency = one rate) are spelled out. There is no explicit when-not or named alternative, but none is needed here.

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