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

Annotations already declare readOnly, idempotent, non-destructive and open-world behavior, so the safety profile is covered. The description adds genuine value beyond that by disclosing the full response payload (category set, is_business, allow/review/block recommendation, reasons, typo suggestion, provider and Workspace/M365 detection), which matters because there is no output schema.

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?

Two sentences, front-loaded with the decision question and followed by the return enumeration; every clause carries information and nothing is padding.

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?

With no output schema, the enumerated return values are essential and present, making the definition largely self-sufficient for a single-address classifier. The remaining gap is the undocumented policy parameter and the absence of routing guidance toward check_batch for volume use.

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 100% for both parameters, so the baseline is 3. The description never mentions the policy parameter or how b2b/strict/lenient shape the recommendation, so it adds no meaning beyond the schema.

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 gives a specific verb+resource framed as a decision question ('Is this a work email or a personal one?') and enumerates the classification outputs, so an agent knows exactly what the tool produces. It does not explicitly contrast itself with siblings like check_domain or check_batch, leaving that differentiation implicit in the name.

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 framing question implies the use case (classifying a single address), but there is no statement of when to use this versus check_domain or check_batch, nor any prerequisites or exclusions. Guidance is left entirely to inference from the name.

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