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

No annotations exist, so the description carries the full load, and it does disclose a lot: cost ($0.003/call), protocol (x402), accepted assets (USDC on Arc/Base/Solana, XNT on X1), and that a real paid call is executed against the target. However, it never states whether the target agent is actually paid by us during the check, what the output verdict looks like, or any latency/rate behavior, so key operational details remain unstated.

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 critical framing ('Before paying an Arc agent') is front-loaded and the measurement list is compact. Some phrasing such as 'Measured, not claimed' and the parenthetical ('outside payers, concentration, self-looking money') is marketing-flavored, but overall little is wasted.

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, multi-step tool with no output schema and no annotations, the description covers pricing, asset options, the two-call handshake, and the substance of the check. The remaining gap is what a caller receives back (verdict fields, failure modes) and the apparent mismatch around the target identifier parameter.

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?

Only one parameter exists and schema coverage is 100%, so the baseline would be 4; the description does add real meaning by explaining that `payment` carries a signed x402 payload and completes the purchase within the call. It is pulled down because the text instructs 'Pass agent, address or url', an input that does not appear anywhere in the schema, creating confusion about how the target is specified.

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 opens with a concrete verb and resource ('trust check' on an Arc agent before paying) and enumerates exactly what is measured: liveness now and over 7 days, response time, payment functionality, a settled paid call, and on-chain payer composition. That is far more specific than the title. It does not explicitly distinguish itself from near-siblings such as arc_agent_reputation or arc_payment_check, which keeps it off a 5.

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 context is stated crisply: 'Before paying an Arc agent'. The two-step protocol (call without payment for terms, sign with your own wallet, call again with payment) tells the agent exactly how to sequence calls. It never names an alternative sibling to use instead when you only want reputation or raw payment verification, so it stops at a strong 4.

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