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

With no annotations, the description carries the full burden and largely meets it: it discloses the exact data sources and lookback windows, the screening lists used, the response fields, and — unusually valuable — the cost model ($0.05 USDC per call, paid via x402 on Base). It does not cover latency, behavior on addresses with no transfer history, or error/refund handling for a paid call, which keeps it below a 5.

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?

Dense but front-loaded: trigger condition first, then screening mechanics, then return values, then price. Every clause carries information and nothing is padding. The opening is a fragment ('Before onboarding or a large payment:') and the second sentence is heavily overloaded, mildly hurting scannability.

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?

No output schema exists, but the description enumerates the return payload (verdict, exposure level, flagged counterparties with sample tx, coverage) and discloses the payment requirement before the call is made. For a single-parameter read tool this is close to complete; only edge-case behavior and timing are unstated.

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% for the single 'address' parameter, so the schema already documents it as an EVM address (0x...). The description adds only indirect context (Base/Ethereum scope confirms EVM-only), with no guidance on accepted formats beyond what the schema says. Baseline 3 is appropriate.

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 states a concrete verb-and-resource: screen an address plus its recent counterparties against OFAC SDN, Circle/Tether freeze lists and exploit/phishing/mixer labels. The depth is pinned down precisely (Base USDC transfers in the last 100k blocks, Ethereum last 50 ERC-20 transfers), which implicitly distinguishes it from shallower siblings like sanctions_screen. It stops short of naming which sibling to use instead, so it is clear but not sibling-differentiating.

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?

It gives a real trigger condition — 'Before onboarding or a large payment' — which is more than most tools offer. However, with five sibling sanctions tools (sanctions_address, sanctions_screen, sanctions_risk, sanctions_batch, sanctions_wallet_profile), no when-not guidance or alternative routing is provided. An agent must infer that 'deep' means the expensive, counterparty-expanded option.

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