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 substantial work: it discloses the x402 payment model, the exact price ($0.002 USDC per call) and network (eip155:8453), the upstream authority (ECB), the fallback behaviour for a pegged BRL, and the fact that values are deterministic and non-estimated. What it does not cover is staleness behaviour — whether the fixing rolls over on weekends/holidays or what happens when no new 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?

Two dense sentences with no filler. The paid/transport tag is placed first as a cost gate, then the purpose statement, then the provenance qualifiers. Every clause — rate date, method, source attribution, no estimate — adds information an agent would otherwise have to guess.

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 adequately covers both what comes back (rate, rate date, derivation method, source attribution) and the payment precondition. The remaining gap is temporal semantics — how fresh the fixing is and what happens between ECB publication days — which matters for a reference-rate lookup.

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 per-parameter meaning to add; baseline is 4. The description is consistent with the empty schema and implicitly confirms the pair is fixed by the tool name rather than by arguments.

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 (CHF/BRL reference rate) and a specific verb/scope (returns the latest European Central Bank fixing), and it distinguishes itself from the hundreds of sibling fx_* pair tools by naming the data source and the derivation method (direct, cross via EUR, or peg-derived). An agent can tell exactly which pair and which kind of rate this returns without opening any schema.

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 by the pair-specific naming: call this for the CHF/BRL rate. However, there is no explicit routing guidance against near neighbours such as fx_convert, fx_latest, fx_timeseries, or the inverse fx_brl_chf — nothing says when to prefer this over a conversion tool or a historical series. The agent must infer the choice from names alone.

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