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

Annotations only declare openWorld/idempotent/destructive hints; the description carries far more: metered billing with per-address cost model (1 credit on first-provider rejection, 2 when both answer), no-verdict = unbilled, duplicates/unparseable dropped before billing, subscription state requirements, specific refusal codes (subscription_not_active, trial_allowance_exceeded), and mid-job allowance exhaustion behavior. This is exceptional disclosure beyond structured 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 the critical 'SPENDS MONEY' warning and organized around billing, eligibility, and next-steps. It is long and dense, but nearly every sentence carries unique billing/error behavior; only minor pruning (e.g., restating the duplicate drop already in the schema) would tighten it.

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 description fills the gap by explaining the full lifecycle: response gives a billed total, per-address verdicts downloadable as CSV, unknown results, and the poll-then-list follow-up. An agent has everything needed to invoke it correctly and safely.

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%, and both parameters (name, emails) are already documented in the schema, including the 50k cap and the duplicate/unparseable drop. The description restates the dedup/billing interaction but adds little parameter-specific syntax or semantics beyond the schema, so the baseline 3 applies.

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+resource (create a verification job over a list) and explicitly contrasts with siblings: 'does NOT create or send a campaign — it verifies a list on its own.' An agent can distinguish it from cancel/get/list_email_verification_job and from campaign creation without reading 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 explicit prerequisites and sequencing: call get_email_verification_rates first for pricing, then poll get_email_verification_job until state is done, then list_email_verification_results for results. Also states when it is refused (past_due, trial limits), which is a genuine usage boundary.

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