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

Annotations cover read-only, open-world, idempotent, non-destructive, so the description doesn't need to repeat safety. The description adds context about the data source, returning status and expiration, and explicitly states that principal-person and direct-contact fields are excluded – useful disclosure beyond annotations. Minor gap: no mention of rate limits or pagination, but the description adequately builds on the annotation baseline.

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 dense but informative, with the key purpose and parameters front-loaded. It proactively mentions what fields are returned and what is excluded, keeping to two sentences. No waste, though it could be slightly more organized.

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 is a simple lookup with no output schema and annotations covering safety, the description covers what the tool does, its source, and its limits (no principal-person fields). It clearly states the accepted input types and the return fields. Missing explicit mention of what happens if no match is found, and does not discuss rate limits, but these are not critical for basic invocation.

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?

Though the schema covers 100% of parameters with descriptions, the main description adds value by stating that license_number is 'Preferred when known' and that business_name is 'partial', enriching the semantics beyond the schema. It also clarifies that limit caps at 25, which is in the schema but the description reinforces the intent.

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 the specific verb 'Verify' and the resource 'Washington contractor registration', against the official L&I API. It also enumerates the exact data returned and what is excluded, distinguishing it from generic search 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 clearly states that it verifies against the official API and accepts either license number or partial business name. It implies when to use it (when you need contractor registration verification) but does not explicitly state when not to use it or compare to siblings like wa_contractor_license_history or wa_contractor_recent_changes. That leaves some gap.

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