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

With zero annotations, the description carries the full behavioral burden and does it well: it discloses the cost and payment mechanism ($0.002 USDC/call, x402, eip155:8453) before the agent commits, states the data is deterministic and non-estimated, explains the ECB-fixing-vs-peg fallback logic, and enumerates the provenance fields returned. What is not covered is failure behavior — e.g. what happens on weekends/holidays when the ECB publishes no fixing, or what occurs if payment settles but the rate 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?

Two sentences, zero waste, and the cost/payment tag is front-loaded so the agent sees the price before the substance. The remainder is dense with disambiguating detail — source, peg fallback, method taxonomy — with no filler or restatement of the tool name.

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, zero-annotation tool with no output schema, the description supplies unusually complete context: source, determinism guarantee, fallback rule, and the shape of the returned metadata. It falls short of 5 only because the exact response field names and numeric formatting (e.g. decimal precision, which leg is the base) are left unstated, forcing the agent to inspect the first response.

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 input schema has zero parameters, so the baseline is 4. The name fully encodes both currency legs (IDR and XAF), meaning the agent supplies nothing and the pair is fixed by tool selection, which the description implicitly confirms by speaking about one specific rate rather than a configurable pair.

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+resource: it returns the official IDR/XAF reference rate, names the underlying source (European Central Bank fixing, or the official peg for XAF), and specifies what accompanies it (rate date, method, attribution). That is far more precise than a tautology. It stops short of 5 because it never positions itself against the obvious siblings in this huge fx_* family, notably fx_convert, fx_latest, and fx_timeseries.

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: 'official' and 'Deterministic, sourced, no estimate' signal this is the authoritative single-pair lookup rather than an estimated or converted figure. There is no explicit when-to-use statement, no exclusion (e.g. use fx_convert for arbitrary amount conversion, fx_timeseries for history), and no guidance on caching or refresh cadence. With hundreds of near-identical siblings, an explicit disambiguation sentence is the main missing element.

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