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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering safety. The description adds valuable behavioral detail: it checks against 'current official' lists, returns explainable matches and provenance, and produces a signed receipt. This goes beyond the annotations and informs the agent about the nature and freshness of the data and the output structure.

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 two sentences, front-loaded with the core action and outputs, then a crisp list of what to avoid. No fluff or repetition; every clause adds essential information. The structure is highly efficient for an agent scanning for key facts.

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?

Given the nested subject object and the checks array, the description provides enough context for correct invocation. It covers the domain, constraints, and outputs sufficiently. It omits exact output formatting details, but the rich annotations and clear purpose make this adequate. The absence of an output schema reduces the responsibility on the description for return values.

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?

With schema coverage at 0%, the description must compensate. It explicitly defines the subject as a 'public business name' and prohibits other entity types, aligning with subject.name and subject.type. The mention of OFAC and GLEIF implicitly explains the checks array enums. However, it does not describe the optional country parameter or the exact format of the checks array, though those are minor gaps.

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 specific verb ('Screen') and a resource ('public business name') against specific data sources (OFAC and GLEIF). It also enumerates the exact outputs (matches, timestamps, SHA-256 provenance, PROCEED/REVIEW/STOP decision, signed receipt) and explicitly lists what it is not (legal clearance, complete KYB, payment authorization, credit decision), clearly distinguishing it from broader evaluation tools.

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 clear usage boundaries by restricting input to 'public business name' and explicitly forbidding submission of people, accounts, borrower data, and similar private records. It also names exclusions ('Not legal clearance, complete KYB...') that guide an agent away from using this for those purposes. However, it does not explicitly reference sibling tools or provide conditional logic for when to choose an alternative.

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