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

Annotations already cover safety (readOnlyHint, idempotentHint, non-destructive, openWorld), so the bar is lower, yet the description still adds useful behavior: live fetch rather than a stale snapshot, and an explicit custody statement that the server never holds a wallet or pays on the caller's behalf. This is material context beyond the structured hints.

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 pricing is front-loaded, which is appropriate, but the same fact is repeated three times ('0.006 USDC on Base via x402', '$0.006 here vs its $0.01', '$0.006 USDC on Base, paid via x402'). The wallet-custody sentence is also echoed in the payment_header schema description, so the prose is longer than the payload warrants.

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?

There is no output schema, so the description should ideally indicate what a screen returns (match/no-match, score, matched alias), but it never describes the response shape. The payment and screening mechanics are complete, yet an agent still cannot predict the result format before calling.

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 description coverage is 100%, so every parameter (name, type, lists, wallet, threshold, payment_header) is already documented in the schema, including the fuzzy-vs-exact match semantics and the notes that 'pep' is not screened. The description mostly restates the type/threshold/lists fields as compatibility knobs without adding new syntax, so the baseline of 3 applies.

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 and resource: 'Screen a name and/or crypto wallet address against the U.S. Treasury OFAC SDN list'. It scopes what is matched (primary names, aliases, digital-currency addresses) and notes it comes live from the official export service. It does not distinguish itself by name from nearby siblings like sanctions_screen_preview, sanctions_delta, or bundle_sanctions_100, so differentiation relies on inference.

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 payment flow is spelled out precisely: call with no payment_header first to get the challenge, then retry with the signed header using the same business arguments. However, there is no guidance on when to choose this tool over sanctions_screen_preview or sanctions_delta, so the sibling-selection question is left unanswered.

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