nex_sms_buy

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

Annotations already flag destructiveHint=true and idempotentHint=false; the description adds crucial context beyond them: partial batch failure is possible, the balance is charged at current server price, and retries are risky without reconciliation. That is exactly the cost/irreversibility information an agent needs for a money-spending mutation.

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?

Purpose and cap come first, then cost and retry safety, so it is well front-loaded. It is dense but each sentence adds a distinct operational constraint; the trailing 'at most 3 attempts per resource flow' is slightly abrupt but not wasteful.

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, non-idempotent purchase with no output schema, the description covers billing, partial failure, and retry safety well. It stops short of telling the agent how to confirm what was actually bought (e.g. via nex_sms_record_list), which would close the loop.

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 carries the burden. It explains the quantity cap ('at most 10 per call') but says nothing about what countryId or projectId mean or where an agent should obtain valid values, despite sibling list tools existing for that purpose.

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 and resource ('Buy cloud phone numbers for SMS verification') plus a hard scope limit ('at most 10 per call'). This clearly separates it from siblings like nex_sms_code_get, nex_sms_release and nex_sms_record_list.

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 says to call it directly when the user's task needs it and carves out a negative case ('a price inquiry is not a purchase request'). It also gives concrete retry policy: reconcile records and billing if the outcome is unclear, max 3 attempts per resource flow.

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