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

Annotations only declare the safety profile (readOnly/openWorld/idempotent/non-destructive), but the description adds materially: the payment model ($0.005 per call via x402/MPP), the exact endpoint to call, and the key behavioral guarantee that 'Bad input is refused before any charge.' That is genuine disclosure beyond what structured fields provide, including the unusual two-step paid-request flow.

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?

Front-loaded with the 'Use when...' trigger and tight, information-dense; every clause carries routing, pricing, or constraint information. It is somewhat cramped with parentheticals and semicolon-chained clauses ('with the response schema and an example; call that URL...') that slightly burden reading, but no sentence 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?

No output schema exists, and the description compensates by explaining the return mechanism — an x402 request containing the response schema and an example — plus cost, input requirements, and failure behavior. An agent has everything needed to call this correctly and knows the alternatives.

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 goes beyond the schema by clarifying the matching semantics: addresses are screened by 'exact address match' while names use a similarity model (min_score/limit). This distinction between the two input modes is a real addition the schema only implies.

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 — screening a crypto address or a person/company name against the official OFAC SDN list — and pins the exact scope ('OFAC SDN match only', 'exact address match'). It explicitly distinguishes itself from wallet_risk, token_risk, and sanctions_screening_batch, so an agent can route correctly without opening any schema.

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?

Gives an explicit trigger ('before paying or trading'), an explicit boundary ('OFAC SDN match only'), and named alternatives with the condition that selects each ('For a broader rule-based risk label use wallet_risk (addresses) or token_risk (tokens); for a list of addresses use sanctions_screening_batch'). Nothing is left to inference.

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