buy_phone_numberPurchase a phone number for this account. Provide an exact number from search_available_numbers, or just an area code to auto-pick. Billing applies to the RevDesk account.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Display name for the number | |
| area_code | No | 3-digit area code to pick from | |
| phone_number | No | Exact number to purchase, E.164 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already mark the action as destructive and not read-only; the description adds the billing consequence and which account level is charged, giving useful context beyond the schema and annotations.
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?
Two compact sentences cover what is done, how to supply the phone_or area choice, and that billing applies. Everything is front-loaded and none of the sentences repeat schema field descriptions verbatim.
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?
No output schema and no guidance on edge cases, such as what happens if both phone_number and area_code are supplied or if neither is supplied. For a destructive, billing-incurring action, an agent needs a bit more about result and exceptional states than this description gives.
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?
The schema fully describes all three parameters, but the description adds the relationship between phone_number and area_code: exact value from search_available_numbers versus auto-pick by area. This value-add goes above the raw schema field descriptions.
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, purchase a phone number, and its target account, so the resource and the action are unmistakable. It also distinguishes itself from search_available_numbers and list_phone_numbers by focusing on the actual buying step.
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?
Clearly instructs when to provide an exact number from search_available_numbers or when to give only an area code for auto-pick. It doesn't explicitly say which situations should not use the tool, but its intended usage context is concrete and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool maps to a distinct resource/action: phone number search/buy/listing, call lifecycle, SMS, usage, and caller IDs. There is no meaningful overlap between tools like list_calls and get_call, since one is a list and the other is a single-record lookup.
All tool names follow a clean snake_case verb_noun pattern: buy_phone_number, list_calls, place_call, send_sms, search_available_numbers. The verbs are specific and consistently reflect the action being performed.
Ten tools is well-scoped for a telephony/product API server. The count covers the essential actions across phone numbers, calls, SMS, usage, and caller IDs without unnecessary duplication or bloat.
The tool set covers the core workflow well: search/buy numbers, list numbers, place/list/get/hangup calls, send SMS, view usage, and list caller IDs. Minor gaps exist such as no way to release a phone number, manage caller IDs beyond listing, or check SMS delivery status, but these do not break the primary use cases.