mcp-server

roamzy_get_esim

Read-onlyIdempotent

Get a specific eSIM by id, including msisdn, status, balance, and the activation block (qr_payload + lpa_url). ⚠️ QR RENDERING: This tool does NOT return a ready-to-display image. Instead, qr_payload contains the LPA URI string. YOU must generate the QR PNG yourself using your code-execution tools (Python qrcode library, JS qrcode npm package, etc.) and offer the resulting PNG as a downloadable file to the user. DO NOT use external QR-generation services — they show ugly UI dialogs in Claude Desktop and require external trust. Local generation gives the user a real downloadable PNG they can save and scan. ALWAYS caption the QR (once generated) with «Your eSIM number: ». The lpa_url field is ONLY for users installing on the SAME phone where they're reading the chat (camera can't scan own screen) — surface it as a text fallback for that case, prefixed «LPA URI (manual entry):». Do NOT show internal IDs (id, display_id, iccid) to the user. ⚠️ ANON-MODE RECOVERY REMINDER: If this is an anonymous Roamzy session (no ROAMZY_API_TOKEN env was set), after presenting the QR you MUST also re-surface the claim_url from the original roamzy_create_order response with this framing: «❗ Be sure to save this recovery link — without it you will not be able to get back to this eSIM from a different Claude chat». If the user has already closed-and-reopened the chat and lost the claim_url, instruct them to contact Roamzy support (call roamzy_support tool) with their MSISDN + NowPayments transaction hash for manual recovery — operator can mint a fresh claim_url. If the user follows up with «how do I contact support» or «refund» — call roamzy_support, not web search.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`esim_id`	Yes	Internal eSIM ULID returned by list_esims or create_order. Never shown to the user.

Output Schema

TableJSON Schema

Name	Required	Description
`esim`	Yes
`activation`	No	Present once the profile is provisioned.
`api_version`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedAug 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "activation": {
+      "description": "Present once the profile is provisioned.",
+      "properties": {
+        "lpa_url": {
+          "description": "Manual-entry fallback for installing on the same phone.",
+          "type": "string"
+        },
+        "qr_payload": {
+          "description": "LPA URI. Render the QR locally — never post it to an external service.",
+          "type": "string"
+        },
+        "qr_render_instructions": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "api_version": {
+      "type": "string"
+    },
+    "esim": {
+      "properties": {
+        "balance_usdt": {
+          "type": "number"
+        },
+        "created_at": {
+          "type": "string"
+        },
+        "display_id": {
+          "type": "string"
+        },
+        "iccid": {
+          "type": "string"
+        },
+        "id": {
+          "description": "Internal ULID for follow-up calls. Never user-facing.",
+          "type": "string"
+        },
+        "msisdn": {
+          "description": "The eSIM number — the ONLY identifier to show a user.",
+          "type": "string"
+        },
+        "status": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "esim"
+  ],
+  "type": "object"
+}

First observedMay 30, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already mark the tool as readOnly and non-destructive. The description goes far beyond by disclosing that the tool does not return a ready-to-display image but a raw payload that must be rendered locally, warning against external QR services, and detailing privacy rules about not showing internal IDs. It also documents the anon-mode recovery obligation, adding valuable behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the tool's purpose, then uses clearly separated sections for QR rendering and anon-mode recovery. It is verbose but each section serves a functional purpose. The emphatic warnings and emoji use slightly reduce elegance, but the structure earns a high score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists and the description covers return fields, activation details, user privacy, and exception handling (support contact), it is nearly exhaustive for this tool's context. It addresses all foreseeable user follow-ups and platform quirks.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The only parameter esim_id is fully described in the input schema with the same text about being an internal ULID and never shown to the user. The tool description adds no new parameter detail beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb 'Get a specific eSIM by id' and enumerates returned fields (msisdn, status, balance, activation block). This clearly distinguishes it from siblings like list_esims (which returns a collection) and create_order (which creates a new resource).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool: whenever a single eSIM's details are needed by ID. It also gives conditional usage guidance for anonymous sessions and recovery flows, including when to call roamzy_support. However, it does not explicitly name alternatives or state 'use this instead of X'.

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

All mcp-server tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.