Top-up plans that fit an eSIM we issued: plan_id, name, gb, days, retail. Order one with create_checkout(plan_id, topup_iccid=iccid) or, from a wallet, purchase_esim(plan_id, client_ref, topup_iccid=iccid).
| Name | Required | Description | Default |
|---|---|---|---|
| iccid | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, idempotent, and closed-world. The description adds useful behavioral context by limiting results to eSIMs issued by the service and by showing the intended usage path through create_checkout or purchase_esim.
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 with no filler: the resource, scope, returned fields, and follow-up actions are all stated economically and front-loaded.
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 single-parameter read-only list tool with an output schema, the description is nearly complete: it gives scope, return fields, and next steps. The only real gap is the under-specified iccid parameter, already counted under parameter semantics.
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 conveys that iccid identifies the eSIM via the 'topup_iccid=iccid' examples, but it never explicitly describes the iccid parameter's format, source, or validation requirements.
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 identifies the resource (top-up plans) and its scope (only eSIMs issued by this service), listing the returned fields. It does not use an explicit verb like 'list', relying on the tool name, and sibling differentiation from get_plans is only implicit.
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 context 'fit an eSIM we issued' implies when to call, and the follow-up calls show how the result can be used. However, it does not explicitly state when to choose this over get_plans or any listing alternatives, nor does it mention prerequisites or exclusions.
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 entity or action: destinations, plans, checkout, wallet purchase, deposits, wallet, orders, usage, top-ups, and payment methods. create_checkout and purchase_esim both place orders but are clearly differentiated by funding source and explicitly cross-referenced in descriptions.
All tool names follow a consistent verb_noun snake_case pattern: create_*, get_*, list_*, search_*, purchase_esim. There are no mixed conventions or vague verbs.
12 tools is well-scoped for an eSIM storefront plus wallet subsystem. Each tool has a distinct role, and none feel redundant or excessive.
The set covers destination discovery, plan selection, checkout and wallet purchases, order tracking, wallet funding, top-ups, and usage checks. Minor gaps exist around cancellation/refund flows and listing non-wallet orders, but the core lifecycle is well covered.