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

With no annotations present, the description carries the full burden and does so: it discloses provenance (ECB statistics), update cadence (~16:00 CET each TARGET day), staleness bound (~90 days), weekend behavior (prior fixing), a reference-only disclaimer, and even the $0.002 USDC x402 cost. These are exactly the traits an agent cannot infer from structured fields.

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 "Use when" trigger, then organized into Input / Output / Source / Example / Price blocks with zero filler sentences. It is slightly dense and mixes operational metadata (pricing, update time) into the same paragraph, but nothing is wasted.

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 fully characterizes the return value (JSON rates for the fixing date, % change vs prior fixing, converted amounts, raw ECB EUR rates). Combined with source, freshness, and cost, an agent has everything needed to call and interpret it.

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, but the description adds meaning beyond the schema: the default base (EUR), the YYYY-MM-DD date format, the weekend prior-fixing rule for date, and a concrete query example (?base=USD&symbols=KRW,JPY&amount=100). That extra semantic context lifts it above 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?

States a specific verb+resource (fetch official daily FX rate / currency conversion), names the currency universe (30 ECB currencies incl. KRW, JPY, CNY), and is unmistakably distinct from every sibling (gas, token flows, weather, sanctions, etc.). An agent knows exactly what this returns 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?

"Use when you need an official daily FX rate or currency conversion" gives clear positive triggering context, and the description scopes the data to the last ~90 days. It does not name an alternative or an explicit when-not, but there is no competing FX sibling to route against, so the guidance is effectively complete.

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