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

With no annotations, the description carries the full burden and does substantial work: it discloses the paid nature ($0.002 USDC/call), the x402 payment scheme and chain (eip155:8453), the data source, that results include rate date, derivation method (direct, cross via EUR, or peg-derived) and source attribution, and that values are deterministic rather than estimated. It stops short of stating update cadence, staleness behavior, or failure modes when a fixing is unavailable.

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?

It is a single dense sentence plus a bracketed pricing tag, with no filler. The compression is heavy — nested parentheticals about pegs and cross rates make it slightly harder to parse — but every clause conveys real information.

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 lookup tool, it covers what is returned (rate, date, method, attribution), the source, and the payment precondition, which is what an agent needs to decide whether to spend a call. Missing only secondary details such as fixing publication time/timezone and what happens when the latest fixing is stale.

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; there is nothing for the description to disambiguate. It correctly signals that the pair and scope are fixed by the tool itself rather than configurable, which is the only parameter-adjacent information that matters here.

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 (the EUR/JPY reference rate) and its provenance (European Central Bank fixing), and explicitly distinguishes it from estimated or computed rates with 'Deterministic, sourced, no estimate.' It does not name the alternative tools (e.g. fx_convert, fx_latest, fx_timeseries) that would be used for conversion or historical series, so sibling routing rests on the pair name alone.

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' and 'no estimate' suggest it should be chosen when an authoritative fixing is required rather than a converted or time-series value. There is no explicit when-to-use/when-not guidance, no mention of how to get a different pair, and no statement about freshness or caching the agent should account for.

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