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

With no annotations supplied, the description carries the full burden and does real work: it discloses the paid x402/eip155:8453 access model and the $0.002 USDC per-call cost, which is critical pre-invocation context an agent cannot get from the empty schema. It also identifies the upstream source (ECB) and the peg fallback, and asserts 'deterministic, sourced, no estimate'. It stops short of describing failure behavior (e.g. weekends/holidays with no fixing) or quoting direction.

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 two-clause sentence, front-loaded with the cost/payment bracket before the substantive purpose, so a paying agent sees the price first. Every clause carries information (source, fallback, returned fields, determinism guarantee). Slightly dense but no 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 tool with no output schema, the description usefully enumerates what comes back — rate, rate date, method (direct / cross via EUR / peg-derived), and source attribution. The main omission is the quotation convention (which currency is base, i.e. units of XOF per 1 BHD) and freshness/fixing schedule, both of which an agent needs to consume the number 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 there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly implies the currency pair is fixed by the tool identity rather than supplied by the caller.

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 and pair: 'Official XOF/BHD reference rate', plus the underlying source (ECB fixing) and fallback (official peg). An agent can distinguish it from the hundreds of sibling fx_* pair tools by the currency codes alone. It does not, however, name alternatives such as fx_convert, fx_latest, or fx_timeseries, which sit in the same family and could be confused with a single-pair lookup.

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 by the pair name and the word 'reference rate' — the agent infers this is the tool for a point-in-time XOF/BHD rate. There is no explicit statement of when to prefer it over fx_convert (for arithmetic), fx_latest (for a bundle of rates), or fx_timeseries (for history), and no note about when the pegged path applies versus the ECB path from a caller's perspective.

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