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

With no annotations, the description carries the full behavioral burden and does well: it discloses the x402 pay-per-call cost ($0.002 USDC on eip155:8453), the data provenance (ECB fixing), the peg-handling fallback, and that the result is deterministic with no estimation. It stops short of stating publication cadence, staleness behavior, or what happens when a fixing 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?

A single dense sentence that front-loads the price/payment tag before the purpose, so cost is visible before commitment. Every clause adds information (source, fallback, returned fields, determinism); the only mild noise is the bracketed protocol metadata, which is still operationally relevant.

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?

There is no output schema and no annotations, so the description must cover both behavior and return shape; it lists the returned fields (rate, rate date, method, source) but does not describe the response envelope, numeric precision, or error behavior when no fixing exists. For a zero-parameter paid lookup this is adequate but leaves gaps an agent would hit on first call.

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 the baseline is 4 and there is nothing for the description to disambiguate. The pair is fixed in the tool name, which is consistent with the empty 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 names a specific resource and scope: the official ILS/CNY reference rate from the latest ECB fixing, including the peg fallback. It is unambiguous which currency pair and which data source, though it never explicitly contrasts itself with siblings like fx_convert (conversion) or fx_latest (multi-pair snapshot), leaving that routing to the name alone.

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: 'Deterministic, sourced, no estimate' signals this is the right choice for audit/compliance-grade rate lookups rather than approximations, but there is no explicit when-to-use statement and no named alternative for conversion or historical series. An agent must infer from the pair name and the word 'reference' that this is a spot-rate lookup, not a calculator.

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