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

With no annotations, the description carries the full burden, and it does disclose real behavior: cost ($0.002 USDC/call), payment protocol (x402, eip155:8453), data provenance (ECB fixing vs official peg), and the derivation method. It adds valuable decision-relevant context, but says nothing about failure modes, staleness bounds beyond 'latest fixing', or what happens if payment is not settled.

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?

A single dense sentence plus a bracketed payment prefix; every clause carries information (source, peg fallback, rate date, derivation method, attribution, determinism). The payment/network metadata leading the description is arguably not the most important element for tool selection, so front-loading slightly favors billing over purpose.

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 does the work of describing the return payload (rate, rate date, method, source attribution), which is the key gap it needed to fill. Remaining omissions — direction convention and freshness/staleness guarantees — are modest for a zero-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?

The tool takes zero parameters, so there is no parameter meaning to add; the baseline of 4 applies. The description correctly signals that no input is required by describing a fixed pair lookup.

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 resource (official AED/USD reference rate) and a specific source/derivation (ECB fixing, or the official peg when the USD is pegged), which is far more than the sibling names alone convey. It stops short of disambiguating quote direction (AED per USD vs USD per AED) or naming the inverse sibling fx_usd_aed, which matters in a family of ~500 near-identical pair tools.

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?

Usage is implied by the pair name and the 'reference rate' framing, and 'Deterministic, sourced, no estimate' hints at when to prefer it over an estimation source. But it never says when to use this instead of fx_convert, fx_latest, fx_timeseries, or the inverse pair, and offers no exclusions or prerequisites.

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