Cancel a quick SMS order that is still waiting for a code and refund it to the wallet immediately. Refused if the SMS was already delivered (read it with check_sms_verification instead). Requires a connected agent wallet.
| Name | Required | Description | Default |
|---|---|---|---|
| orderId | Yes | The Order ID of the waiting quick SMS order |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds context beyond annotations: immediate refund to wallet, refusal if already delivered, and the wallet requirement. Annotations indicate readOnly=false and destructiveHint=false, and the description aligns with this (mutation but not destructive in the sense of data loss). No contradiction, but it could mention error handling or side effects of cancellation.
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 sentences front-load the primary action and refund, followed by a conditional exception and prerequisite. All information is relevant with no redundancy or fluff.
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 simple one-parameter tool with annotations, the description covers the core behavior, refund, failure condition, alternative, and prerequisite. Missing only explicit return value information, but given no output schema and low complexity, this is acceptable.
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 100% and the parameter description already states 'Order ID of the waiting quick SMS order'. The tool description does not add additional semantic meaning beyond what the schema provides, hence baseline score.
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?
The description clearly states the tool cancels a quick SMS order and refunds it, distinguishing it from other cancellation tools like cancel_sms_rental and from the read-only check_sms_verification. The verb 'Cancel' is specific and the resource is well-defined.
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?
Provides explicit usage conditions: 'still waiting for a code' indicates when to use, and 'Refused if the SMS was already delivered' gives a clear exclusion with an alternative tool named ('check_sms_verification instead'). Also mentions the prerequisite of a connected agent wallet.
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.
There is notable overlap between search tools (search, search_esim_packages, search_phone_plans) and detail tools (fetch, get_package_details, get_pricing, get_phone_plan_pricing). While descriptions clarify some differences, agents may struggle to pick the right tool without careful reading, especially between 'search' and 'search_esim_packages' and between 'fetch' and 'get_package_details'.
Most tools follow a clear verb_noun convention (e.g., purchase_esim, list_orders, get_balance). A few are single verbs like 'fetch' and 'search', which stand out but are still recognizable as actions. Overall the pattern is predictable and readable.
With 31 tools, this is a large set. The server covers several distinct sub-domains (eSIM data, phone-number eSIM, SMS verification, SMS rentals, wallet management), which justifies some size, but the count is on the high side and could be consolidated (e.g., merging search tools or detail-fetching tools).
The tool surface covers the full lifecycle for each product line: search, view details, purchase, list, check status, top-up/cancel, plus wallet management. The only minor gap is a lack of explicit update tools (e.g., changing a phone plan), but core workflows are well supported.