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

The description discloses background execution with up to 10 parallel KYC calls, immediate job_id return, polling with kyc_screener_batch_result, and webhook callbacks. This goes beyond the annotations (readOnlyHint, destructiveHint) and provides substantial behavioral context.

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 front-loaded with core behavior and provides rich context about job polling and webhooks. It is slightly verbose where it summarizes entry fields already present in the schema, but remains efficient overall.

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?

Covers job submission, result retrieval, webhook alternative, use cases, and limits. The async parameter ambiguity and lack of error handling or job retention details prevent a higher score, though the output schema likely covers 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?

While schema coverage is 100%, the description introduces ambiguity with the `async` parameter. It states the tool 'returns immediately (<300ms) with a job_id', implying it is always async, but the schema's `async` parameter suggests it can be toggled (true or false) with a different timing (<200ms). This inconsistency could lead to incorrect invocation.

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 'Async batch variant of kyc_screener' and explains it accepts 1-100 names, returning a job_id immediately. This distinguishes it from the sibling kyc_screener and the result tool, giving a specific verb, resource, and scope.

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?

Explicitly lists use cases: 'bulk client onboarding, UBO list screening, or periodic AML refresh batches.' It also provides alternatives like registering a webhook via webhooks_manage instead of polling, showing clear when-to-use and alternative guidance.

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