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

Annotations declare readOnlyHint=true and openWorldHint=true, which already inform safety and data freshness. The description adds valuable context beyond annotations: the oracle reflects current designations including removals (an address may screen clean after delisting), and it explicitly states the oracle does not return programme-level case detail. This transparency about dynamic data and output limitation goes beyond what annotations cover.

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 description is efficiently structured: first sentence states purpose, second explains the oracle's dynamic nature, third describes the output and limitation, fourth lists use cases. No redundant sentences; every part earns its place. Information is front-loaded with the core function, making it easy for an agent to quickly parse.

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?

For a single-parameter tool with no output schema, the description is remarkably complete. It covers what the tool does, how the data behaves (open-world), what the output is (boolean), and its limitation (no case detail). It also provides practical guidance (when to use). There are no obvious gaps for an agent to call it correctly.

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 single parameter 'address' is fully described in the schema (EVM address format). The description adds little to parameter semantics—it reuses the same format but adds the screening purpose and use-case context. Since the schema already documents the parameter, the baseline of 3 applies; the description does not introduce new field-level meaning.

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 opens with the exact function: 'Sanctions screening for a crypto wallet address' and names the specific oracle (Chainalysis) and coverage (OFAC SDN, EU, UN). It also states the output is a boolean, distinguishing it from sibling tools like screen_name (name-based) and verify_uk_company/verify_us_company (company verification), which are clearly different domains.

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 description gives explicit use cases ('Use for AML compliance, counterparty due diligence, and payment screening before sending USDC or any funds to an address'). While it doesn't explicitly say 'do not use for name/company screening' or name alternatives, the purpose is so specific that an agent can infer when this tool applies versus siblings. It lacks an explicit when-not or alternative routing, but the context is strong enough.

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