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 well: it discloses the paid invocation ($0.002 USDC via x402 on eip155:8453), the data provenance (ECB fixing or official peg), the derivation method, and that results are deterministic and not estimates. It stops short of describing failure behavior for unavailable or stale fixings, or rounding and quote conventions.

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?

Essentially two sentences (plus a trailing qualifier) with no filler, and the paid-invocation tag is front-loaded so the agent sees the cost before reading the substance. The colon-separated payload listing ('with the rate date, the method... and the source attribution') is slightly dense but earns its place by previewing return fields.

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 no-parameter lookup with no output schema, the description covers what an agent needs: what value is returned, its source, the cases where derivation differs, and that the response includes rate date, method, and attribution. The main remaining gap is the quote convention (units per 1 AED) and what happens when no fixing exists for the date.

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 beyond the pair identity, which it does cover. Baseline 4 applies for a parameterless tool where the schema requires no explanation.

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 the exact resource (AED/XAF), the authoritative source (European Central Bank fixing), and the fallback case (official peg when XAF is pegged), so an agent knows precisely which pair and which rate family this returns. It also implicitly separates this official reference rate from generic market-rate siblings via the 'cross via EUR or peg-derived' method note.

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: the agent must infer this is the tool to call when it needs an official ECB reference rate for AED/XAF. No alternatives are named despite near-identical siblings such as fx_convert, fx_latest, fx_timeseries, or fx_eur_xaf for cross-rate purposes, and no when-not-to-use conditions are given.

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