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

With no annotations at all, the description carries the full disclosure burden and does a good deal of it: it discloses the paid x402 model at $0.002 USDC per call on eip155:8453, the upstream source (European Central Bank), the derivation method (direct, cross via EUR, or peg-derived), and the determinism guarantee. That is meaningful operational context an agent cannot get from the empty schema. It stops short of stating rate limits, caching or refresh cadence, or error behavior when no fixing exists.

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?

The description is two sentences and front-loads the most decision-relevant fact, the price. The second sentence is dense but each clause (pair, source, peg handling, returned metadata, determinism claim) earns its place. Minor cost: the bracketed payment preamble before the purpose statement delays the actual subject slightly.

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, single-value lookup with no output schema, the description covers the essentials an agent needs: what is returned, where it comes from, how the rate is derived, and what it costs. It is not fully complete, since it never describes the shape of the returned payload or what happens if no ECB fixing exists for a date, but those are secondary for a no-arg read 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 and the baseline of 4 applies. The description correctly spends no space restating inputs and instead describes the output fields (rate date, method, source attribution), which is the most useful thing it can do given the empty input 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?

The description states a specific verb and resource: it returns the official BGN/AUD reference rate, specifically the latest ECB fixing or the official peg. That is precise enough for an agent to know exactly which currency pair and which rate class it gets. It loses a point only because, in a family of hundreds of near-identical fx_* siblings, it never names the related tools (fx_convert, fx_latest, fx_timeseries) that an agent would otherwise need to disambiguate against.

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 rather than stated. Phrases like 'reference rate' and 'Deterministic, sourced, no estimate' hint that this is for official/audit-grade rate lookups rather than ad hoc conversion, but there is no explicit when-to-use, no exclusion of the fx_convert sibling, and no guidance on staleness or fallback if a fixing is unavailable. An agent must infer the selection criteria from the wording.

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