nex_mail_buy

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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description builds on that with concrete consequences: it charges the balance at the current server price, there is no custom prefix, no renewal and no refund. The retry cap and "reconcile records and billing before any retry" instruction directly address the non-idempotent, money-spending risk the annotations signal.

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?

Five short clauses, front-loaded with the action and the variant split, then pricing, then retry safety. No sentence is redundant — each contributes either a constraint or a decision rule.

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 destructive, balance-charging purchase with no output schema, the description covers the money, the refund policy and the failure/retry path thoroughly. The one remaining gap is that it never hints at what a successful call yields (mailbox identifier, address, expiry), which matters more given there is no output schema to fall back on.

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 50% (only suffix and domainId are documented), and the description fills that gap by tying suffix to MAINSTREAM ("needs a supported suffix") and domainId to TEMPORARY ("may take a domainId"). It says nothing extra about type or durationHours, but both are closed enums whose intent is clear from their values, so the incremental loss is small.

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?

"Buy a receiving mailbox" gives a specific verb and resource, then immediately splits the resource into its two variants (MAINSTREAM vs TEMPORARY) with their distinguishing constraints. An agent can tell this apart from nex_mail_plan_list, nex_mail_record_list and the other mail siblings 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?

Explicitly states when to call ("call it directly when the user's task needs it") and when not to ("a price inquiry is not a purchase request"), which routes the agent away from this paid action toward an inquiry path. It also bounds retries ("At most 3 attempts per resource flow") and requires reconciliation before any retry when the outcome is unclear.

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