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

Substantial value beyond the annotations: per-request credit cost including repeats, the confirm gate, the 15-second result window, and the two possible return shapes (final result vs. queue/verifying task ID). Annotations already declare readOnly=false and idempotent=false, but the description makes the cost/non-idempotency consequence concrete rather than abstract. It stops short of describing auth requirements or error/failure behavior.

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 the action, then cost, precondition, return behavior, and the follow-up route — no filler sentences. The final sentence about basic-only mode returning unknown/score -1 is useful but slightly opaque without context on which mode is being invoked.

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?

For a non-idempotent, credit-consuming action with no output schema, the description covers cost, precondition, latency window, return shapes, follow-up, and one edge-case result. The remaining gaps are disable_catchall_verify's semantics and error handling, which leave the agent slightly under-informed for a paid write operation.

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 0%, so the description must compensate. It explains confirm (must be true) and, implicitly, the email param, but disable_catchall_verify is never mentioned — the closing sentence about catch-all/SEG-protected addresses gestures at that concern without naming the parameter or saying what toggling it does. Partial compensation only.

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?

Opens with a specific verb and resource ('Verify one email') and scopes it to regular mode, which cleanly separates it from create_bulk_verification and the bulk_* siblings. It also names bounceban_single_status as the follow-up reader, so the agent can place it in the workflow without opening any 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?

Gives a hard precondition ('requires confirm:true'), a follow-up route ('Read that existing ID with bounceban_single_status later'), and an explicit prohibition ('Never resubmit simply because it is still pending'). What's missing is an explicit statement of when to prefer bulk verification for many addresses.

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