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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description is consistent with them. It adds genuinely non-obvious behavior: a $0.25 charge against the API key balance and the verdict/score/receipt return shape. No auth or rate-limit details, but the cost disclosure is the key trait an agent needs.

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 dense paragraph, front-loaded with the checks, then outputs, then cost, then the one piece of caller guidance. Every clause carries information, though the parenthetical check list is long enough to verge on enumeration bloat.

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 steps in and describes the return values (verdict, 0-100 score, explained findings, signed receipt), which is exactly what's needed. It covers a 3-param nested schema and cost, leaving only minor gaps like failure modes when required fields are absent.

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 only 33% (many nested payment/context fields lack descriptions), so the description must compensate — and it does by explaining that 'context' should be filled with everything known about how the payment arrived and that it materially improves detection. It does not explain individual nested fields like 'requested_urgency' or 'bank_details_changed', so it is helpful but not fully compensatory.

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?

Names a specific verb+resource ('pre-payment risk check on a payee') and enumerates the exact checks performed (OFAC, domain age, lookalikes, routing/IBAN/SWIFT/wallet validation, BEC signals). This distinguishes it from sibling screen_sanctions (a subset) and verify_receipt (which consumes its output).

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?

The title and first clause make the when-to-use case explicit ('before paying'), and it tells the agent to populate 'context' with everything known about how the request arrived. It stops short of naming siblings or stating when not to use it (e.g. vs screen_sanctions).

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