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

With no annotations at all, the description carries the full burden and does well: it discloses payment terms ($0.002 USDC, x402, eip155:8453), the authoritative source (ECB), fallback behavior when EUR is pegged, the computation method (direct, cross via EUR, peg-derived), and that the value is deterministic rather than an estimate. It does not cover freshness/staleness for weekends and holidays, which is the main behavioral gap for a reference-rate tool.

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?

Two tight sentences, front-loaded with pricing then purpose, and every clause contributes information (source, fallback, method, attribution, determinism). The bracketed payment header is dense jargon but is genuinely load-bearing for a paid x402 endpoint.

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?

For a zero-parameter, no-output-schema, no-annotation tool, the description covers what the value is, where it comes from, how it was derived, and which fields accompany it. Remaining gaps are error/staleness behavior and the inverse-pair question, both achievable with one more sentence.

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 tool takes zero parameters, so the baseline is 4 and there is no parameter meaning for the description to add. The pair is fixed by the tool name, which is coherent with an empty 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?

Names the exact currency pair (MYR/EUR), the specific artifact (latest ECB fixing, or the official peg when EUR is pegged), and the fields returned. Because the pair is encoded in the tool name and repeated in prose, an agent can distinguish it from the hundreds of sibling fx_* pairs without opening a 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?

The description implies usage (reference/official rate, 'no estimate') but never states when to prefer this over directional or generic siblings such as fx_eur_myr, fx_latest, fx_convert, or fx_timeseries. Directionality is critical for an FX pair and is left entirely implicit — nothing warns that this returns MYR-to-EUR and not the inverse.

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