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

Annotations only cover read-only and closed-world; the description adds the verdict taxonomy, the one-sentence advice, the specific evidence classes returned (incoming payments, repeat buyers, delivery reports, service liveness), and that it is free and needs no key. It also warns about the consequence of a stop verdict, which is action-guiding behavior an agent cannot infer elsewhere.

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 imperative warning is front-loaded, followed by the return contract and the do-not-pay rule. Every sentence carries decision-relevant information with no filler.

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, the description carries the return contract itself: verdict tiers, advice sentence, and evidence categories. Combined with the trigger condition and auth/cost note, an agent has everything needed to decide when and how to call it.

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 baseline is 3; the description still adds meaning by identifying where the address comes from (e.g. the payTo of an x402 402 response). It adds little extra on amount_usd beyond what the schema already says about large payments needing a stronger record.

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 concrete verb (check) and resource (a payment/wallet) plus the exact output shape (ok/careful/stop verdict with evidence). It is clearly distinct from siblings like check_trust or wallet_history because it is scoped to a prospective payment decision rather than general reputation or history lookup.

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?

"CALL THIS BEFORE PAYING ANY SELLER" gives a precise trigger, and "If the verdict is stop, do not pay" defines the follow-up action. It does not explicitly compare against alternatives like check_trust or wallet_history, so it stops short of a full when-vs-what-else routing statement.

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