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: paid access at $0.002 USDC per call via x402 on eip155:8453, ECB as the authoritative source, peg fallback, and that values are deterministic rather than modeled. What it omits is equally behavioral — caching/freshness guarantees, what happens before the next ECB publication, and failure/payment-error handling.

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 after a bracketed payment/transport tag; the core resource is front-loaded and every clause (source, peg fallback, returned metadata, determinism) adds information. The bracketed prefix is operationally relevant rather than filler, though it does compete with the purpose for first-read attention.

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?

There is no output schema, so the description must convey return semantics, and it partially does by promising rate date, method, and attribution. It never states the quoting convention (NOK per ILS vs ILS per NOK), numeric precision, or the response envelope, which are the details an agent needs to consume an FX value correctly.

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 nothing for the description to disambiguate. It instead describes the payload conceptually (rate date, derivation method, source attribution), which is appropriate for a parameterless 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?

The description names a precise resource — the official NOK/ILS reference rate sourced from the ECB's latest fixing — and specifies fallback semantics (official peg when ILS is pegged). That is far more specific than the name alone. It does not, however, distinguish itself from related siblings such as fx_convert, fx_latest, or fx_timeseries, which an agent must infer from the pair-naming convention.

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 only implied: an agent needing a sourced NOK/ILS spot reference rate is the obvious caller. There is no explicit when-to-use/when-not, no routing to fx_convert for arithmetic or fx_timeseries for history, and no statement about staleness tolerance. The 'no estimate' note is the only implicit exclusion.

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