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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description's 'Screening' aligns with read-only behavior. The description adds that inputs are validated server-side and the output is 'audited', which provides some extra context. However, it does not disclose details like rate limits, result format, or any data retention implications, so it adds limited value beyond the annotations.

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 but includes marketing fluff ('Gapup agent-payable C-suite expertise (RISK)') and a verbose reference case. The reference case adds some context but could be trimmed. Overall, it is not well-structured; key information is buried among promotional language.

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 tool's complexity (nested objects, 5 parameters, no output schema), the description is insufficient. It does not explain the deliverable's structure, how to handle async execution (despite the async parameter existing in schema), or how results integrate with other tools. The absence of output schema makes the description's lack of return-value details even more impactful.

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 only 20%, so the description should compensate by explaining parameter meaning. It does not; it merely says 'send the documented case fields', which is a pointer to the schema rather than added semantics. The tool's nested objects (entities, screeningScope, onboardingPacket) are not explained in the description, leaving the agent to infer from names and enums.

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 clearly states the tool performs KYC/AML/sanctions screening and returns a structured deliverable. The verb 'Screening' plus resource 'KYC / AML / Sanctions' makes the core purpose clear. However, it does not differentiate from sibling tools like kyc_screener_batch or sanctions_screener_multi, missing an opportunity to clarify its specific niche.

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 provides a reference case but offers no guidance on when to use this tool versus alternatives. There is no mention of batch vs. single screening, sanctions-only vs. full KYC, or any exclusions. The 'send the documented case fields' instruction is functional but not usage guidance.

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