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

With no annotations, the description carries the full behavioral burden and does meaningful work: it discloses the paid cost and payment protocol ($0.002 USDC via x402 on eip155:8453), the upstream source (ECB fixing), the fallback behavior when USD is pegged, and that values are deterministic rather than estimated. What it omits is payment failure handling, rate limits, and how stale a fixing can be relative to the current date.

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 compact sentences with the billing/transport metadata bracketed and front-loaded before the substantive description, so a caller learns the cost before committing. Every clause — pair, source, companion fields, method taxonomy, determinism claim — carries information; nothing is filler.

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 lookup with no output schema, the description covers the essentials: the exact pair, the authoritative source, the companion metadata fields returned, and the monetary cost of the call. The absence of an output schema makes the enumerated return fields (rate date, method, source attribution) especially valuable. Only the freshness/payment-failure story is left thin.

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 nothing for the description to disambiguate and the schema already shows an empty object. The description correctly implies a bare call with no arguments and instead spends its words on what the response will contain, which is the right allocation of effort.

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 names a specific resource and verb of sorts: the official NZD/USD reference rate as published by the ECB, plus what metadata accompanies it (rate date, method, source attribution). It is unambiguous what data comes back. It does not, however, distinguish itself from siblings such as fx_convert, fx_latest, fx_timeseries, or the inverse fx_usd_nzd, leaving the agent to infer that this is the fixed-pair reference endpoint.

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 rather than stated: 'official reference rate', 'deterministic, sourced, no estimate' signals this is for authoritative/compliance-grade quoting rather than ad-hoc conversion, which is a useful cue. But there is no explicit when-to-use or when-not, and no routing to fx_convert for arbitrary pairs or fx_timeseries for history.

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