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

With no annotations, the description carries the full burden and does a fair amount of work: it discloses the x402 payment protocol, exact cost ($0.002 USDC/call), the chain (eip155:8453), the data source (ECB), and the peg-fallback behavior. It also names three fields the response carries (rate date, method, source attribution). What it omits is quoting convention and precision — e.g. whether the value is '1 SGD = X CAD' — and whether a stale or missing fixing returns an error.

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 front-loaded sentence that leads with the cost/transport tag and then the resource, with no filler. It is dense — two parentheticals and a three-item method list — but every clause carries information. Minor cost: the peg caveat sits mid-sentence where it is easy to skim past.

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, no-output-schema tool, the description supplies the things an agent cannot get from structured fields: price, payment rail, data provenance, fallback behavior, and the method field that explains cross-vs-direct derivation. Adding the return value's quoting convention and precision would make it complete for an agent that must parse the number without a schema.

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 of 4 applies. The description correctly implies nothing needs to be supplied beyond payment, and the empty schema is consistent with a fixed-pair endpoint. No parameter meaning is left ambiguous because there are no parameters.

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 — the official SGD/CAD reference rate — with the source (ECB fixing) and the fallback (official peg when CAD is pegged). The currency pair is unambiguous from the name and restated in prose. It does not differentiate itself from siblings such as fx_sgd_usd (different pair) or fx_convert (actual conversion), which are the two nearest alternatives an agent would weigh.

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: 'Deterministic, sourced, no estimate' tells the agent this is for an authoritative reference rate rather than a computed conversion, and the price line signals a paid call. But there is no explicit 'use this instead of fx_convert when...' or 'do not use for historical series — see fx_timeseries', leaving the agent to infer routing among hundreds of fx siblings.

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