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

Annotations only say readOnly and openWorld; the description adds substantial behavior the agent could not otherwise know: flat $0.06 price covering sellers up to $0.05, no charge without a result, the pay-safety precheck rules (only 'pay', payTo must match verified listing, canonical USDC on Base), the ranking signals used, and how payment is passed via _meta['x402/payment']. It also surfaces that funds move from Hearth's wallet — a real financial side effect that the readOnlyHint alone would not convey.

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?

The purchase-and-pricing facts are front-loaded correctly, but the middle becomes a dense run-on enumerating ranking internals ('nightly free liveness probes', '402index reliability, vet402 verdicts', 'rankScore') that do not help an agent select or call the tool. The example output earns its space since no output schema exists.

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 paid, open-world tool with no output schema, the description supplies an example response shape, the price and charge policy, the payment handoff, and a free alternative endpoint — enough to call it confidently. Remaining gaps are failure semantics: what happens if the seller fails or the precheck rejects, and whether a retry is billed.

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?

Schema coverage is 100%, so the four properties are already documented; the description still adds meaning by enumerating the intent categories the classifier assigns, which explains what happens when 'category' is omitted. It also documents a de facto parameter absent from the schema (_meta['x402/payment']), which is genuinely useful invocation knowledge.

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 opening sentence gives a concrete verb and resource: 'Buy any x402 API through Hearth', then explains the mechanism (classify intent, rank sellers, precheck, pay, return response + provenance). An agent knows exactly what the tool does. However, it never differentiates itself from the near-identically-named sibling 'route', nor from x402_discover/x402_precheck, so the buyer-vs-browser distinction must be inferred.

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?

There is no explicit when-to-use statement, no exclusions, and no named alternatives despite 32 siblings including 'route', 'x402_discover', 'x402_precheck', and several native capabilities (ai_chat, ai_summarize) that overlap. The only guidance-adjacent content is the free preview URL and the note that it is not charged unless a result is returned. Usage is implied by the verb 'buy', not stated.

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