Browse purchasable offers: mobile top-ups, travel eSIMs, prepaid bills, or international payment corridors (bank / mobile money / UPI) for a country. Free. Prices shown are indicative; the quote fixes them.
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | payout = international payment (bank / mobile money / UPI) | |
| brand | No | ||
| country | No | ISO-3166 alpha-2, e.g. IN |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. 'Browse' implies a read-only action, and 'Free' plus 'Prices shown are indicative' add practical context beyond the name. However, it does not explicitly confirm no side effects, authentication requirements, or error behavior, which would be important with no annotation support.
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?
The description is two sentences, front-loads the purpose and offer categories, and adds a useful pricing caveat. There is no filler or repetition of schema fields.
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 browse tool, the description is close to sufficient: the required `type` is documented in the schema, country scope is stated, and the relationship to `quote` is clear. But with no annotations and no output schema, the undocumented `brand` parameter and the lack of any return-shape or pagination guidance leave meaningful gaps.
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 67%: `type` and `country` are documented, but `brand` is not. The description reinforces the enum categories and the country scope, but it does not clarify what `brand` means or how it interacts with `type` and `country`, leaving a real semantic gap.
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 opens with a specific verb and resource, 'Browse purchasable offers,' then enumerates the exact offer families: mobile top-ups, travel eSIMs, prepaid bills, and international payment corridors. This clearly separates it from siblings like `buy` and `quote`, especially with the pricing caveat that the quote fixes prices.
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?
The description provides clear context for when to use the tool: to browse offers for a country, and it explicitly hands off firm pricing to the `quote` tool ('Prices shown are indicative; the quote fixes them'). It does not explicitly list exclusions or when to prefer `buy` or other siblings, but the context is strong.
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 has a distinct role in the purchase lifecycle: browsing offers, looking up numbers, quoting, buying, checking orders, and verifying receipts. Some overlap exists between list_offers and lookup_phone, and buy and quote require careful reading, but the descriptions resolve the boundaries.
Names mix noun-only tools (ledger, fx), bare verbs (buy, quote), and verb_noun pairs (list_offers, lookup_phone, verify_receipt, order_status). All are lowercase with underscores, so they are readable, but the naming pattern is not consistent.
Eight tools is well-scoped for a top-up and payment service. Each tool maps to a necessary step or informational need, with no obvious bloat or redundancy.
The core lifecycle is covered: discover offers, quote, buy, check order status, and verify receipts. Minor gaps exist such as no explicit quote cancellation or order history listing, but the public ledger and expiry mechanism mitigate these.