netx-mcp 0.3.1: fix alarm paging, tool-level arg errors, leaner outputs.

- queryNmsAlarms no longer silently clamps page to 2; add is_cleared.
- Bad integer args return invalid_argument tool errors instead of JSON-RPC crashes.
- Nested {"ok": true, "data": {"ok": false}} results are flagged isError.
- stdio: answer ping, never respond to notifications, version from metadata.
- getNmsNe resolves exact host_name/IP; severity lowercased.
- Outputs use nms_ne_id/source=nms; drop ME{uuid} names, echoed field lists, idle hop_* fields.
- Fabric paths: parallel links count as one hop (edges[].parallel_links).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

packages/netx-mcp/README.md

@@ -38,7 +38,7 @@ python -m netx_mcp
 
 [`mcp.json`](./mcp.json) — `command: python`，`args: ["-m", "netx_mcp"]`，`env` 见文件。
 
-## 工具（14）— skill 组 **ops**（`netx-ops`）
+## 工具（15）— skill 组 **ops**（`netx-ops`）
 
 **NMS**（模型面通用名；当前适配器 zte-ume，REST 仍 `/v1/ume/*`）：  
 `queryNmsAlarms`, `aggregateNmsAlarms`, `runNmsDiagnostics`, `queryNmsNeInventory`, `getNmsNe`, `queryNmsAlarmsRaw`, `aggregateNmsAlarmsRaw`, `listNmsAlarmFields`, `sqlQueryNms`
@@ -46,6 +46,8 @@ python -m netx_mcp
 **Managed CLI + paths**（问「能否登录」必须走这里，不要只查 inventory）：  
 `listManagedNe`, `getManagedNe`, `execManagedNe`, `getNeExecJob`, `listCliTargets`, `findTopologyPaths`
 
+0.3.1：`getNmsNe` 可直接传 host_name/IP；输出统一 `nms_ne_id` / `source=nms`；参数类型错误返回工具错误而非协议崩溃。
+
 参数优先 `nms_ne_id` / `nms_ne_ids`（保留 `ume_*` 别名）。
 
 拓扑画布 / Fabric → skill **topology** / [`netx-topology-mcp`](../netx-topology-mcp)（见 [docs/MCP_TOPOLOGY.md](../../docs/MCP_TOPOLOGY.md)）。