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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses parallel execution, per-domain DNS caching, per-unique-address billing, and 'No logging of addresses' — privacy and cost facts not derivable from structured fields. It also enumerates the status values and result fields.

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?

Front-loaded with purpose and the sibling equivalence, then cost, then example, then response shape and privacy note. Dense but every clause carries new information; no filler.

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?

Even though an output schema exists, the description usefully previews the status enum, score range, and confidence fields, and covers cost, privacy, and performance expectations. Nothing material for correct invocation is missing.

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 coverage is 100%, so the baseline is 3; the description adds meaning by tying dedupe to billing ('charged per unique address') and showing an example call with smtp_check false. It does not explain check_policy or the performance tradeoff of smtp_check beyond what the schema already says.

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 a specific verb (verify) and resource (a list of emails), explicitly frames it as the batch counterpart to verify_email, and summarizes the return shape. An agent can distinguish it from the singular sibling without opening the schema.

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?

'Same checks as verify_email for a list' gives clear context that this is the multi-address variant, and the example plus 'Charged per unique address' signals cost-sensitive bulk use. It stops short of explicit when-not guidance or naming a threshold at which verify_email should be preferred instead.

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