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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: price ($0.01), payment rail (USDC on Base only), the fact the tool never executes the check, refusal-before-charge behavior, full-price-on-partial-data rule, and data staleness (up to 30 minutes old). These are exactly the operational details an agent needs before committing funds.

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?

Information density is high, but the text is a run-on paragraph with repeated content ('USDC on Base only' appears at both start and end, and the 'refused and not charged' rule is stated twice). The key fact (quote only, never pays) is front-loaded, but legal/attribution boilerplate interrupts the operational rules.

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?

With no output schema and no parameters, the description carries the burden well: it covers price, rail, request shape, refusal rules, data contents (1M–30Y tenors plus 2s10s and 3M/10Y spreads), and freshness. It does not describe what the returned payment-terms payload looks like, which would help an agent know what to expect back.

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 is empty (0 params), so all parameter knowledge comes from the description, which fully specifies the downstream query parameter: optional date=YYYY-MM-DD, defaulting to the latest published day, plus the refusal behavior for invalid dates. Without this text an agent could not construct the correct request.

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 verb+resource: 'Returns the payment terms for https://horizonpulse.dev/api/treasury/yield-curve', and immediately disambiguates the action by saying 'this tool never runs the check or pays'. The named endpoint distinguishes it from siblings like treasury_debt_quote, though no sibling is explicitly named as an alternative.

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?

Explains the workflow clearly: get the quote, then pay the 402 over HTTP with x402 v2 using GET with no parameters or ?date=YYYY-MM-DD. It also specifies when charges do and don't apply ('Bad input is refused before payment, not charged'; 'If no curve exists for the date, it is refused and not charged'). It stops short of routing to alternatives such as x402_check or treasury_debt_quote for other data.

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