Opservo

Kubernetes cluster snapshot

get_kubernetes_snapshot

Read-onlyIdempotent

Returns the state of one Kubernetes cluster connected to Opservo: version, node conditions and capacity, workloads with ready counts and restarts, problem pods with their reason, last exit code and recent log lines, and recent warning events. Answers only for a cluster (kind kubernetes); a Linux server returns an error saying so.

Input Schema

Name	Required	Description	Default
`agent_id`	Yes	The server/agent UUID to query.

Output Schema

Name	Required	Description
`pods`	No
`error`	No	Present only when the call failed: why, in plain English (unknown server, server from another workspace, not a Kubernetes cluster).
`nodes`	No
`events`	No	Recent warning events.
`version`	No	Kubernetes server version.
`workloads`	No
`collected_at`	No	When the snapshot was taken, ISO 8601.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 16, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "collected_at": {
+      "description": "When the snapshot was taken, ISO 8601.",
+      "type": "string"
+    },
+    "error": {
+      "description": "Present only when the call failed: why, in plain English (unknown server, server from another workspace, not a Kubernetes cluster).",
+      "type": "string"
+    },
+    "events": {
+      "description": "Recent warning events.",
+      "items": {
+        "additionalProperties": true,
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "nodes": {
+      "additionalProperties": true,
+      "properties": {},
+      "type": "object"
+    },
+    "pods": {
+      "additionalProperties": true,
+      "properties": {
+        "problems": {
+          "description": "Pods with a problem: reason, last exit code, restarts, recent log lines.",
+          "items": {
+            "additionalProperties": true,
+            "properties": {},
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "type": "object"
+    },
+    "version": {
+      "description": "Kubernetes server version.",
+      "type": "string"
+    },
+    "workloads": {
+      "additionalProperties": true,
+      "properties": {},
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

First observedOct 15, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuinely new behavior: the type-mismatch error path for non-Kubernetes agents and the specific shape of diagnostic data returned (pod reasons, exit codes, recent log lines).

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?

Front-loaded with the core operation, followed by a dense enumeration of returned fields and then the scoping caveat. It is a single long sentence plus a short one; every clause carries information, though the long enumeration borders on verbose.

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?

An output schema exists, so return values are already covered structurally, yet the description still previews the key contents in a useful way. The error-path disclosure closes the main remaining gap for a single-parameter read tool.

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?

With only one parameter at 100% schema coverage, the schema already fully documents agent_id. The description's phrase 'one Kubernetes cluster connected to Opservo' implies the id selects a cluster but adds no syntax or constraints beyond the schema, 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?

States a specific verb and resource ('Returns the state of one Kubernetes cluster') and then enumerates the concrete contents (version, node conditions, workloads, problem pods, warning events). This clearly distinguishes it from siblings like get_server_overview and get_services, so an agent can route without opening other schemas.

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?

Explicitly scopes the tool: 'Answers only for a cluster (kind kubernetes); a Linux server returns an error saying so' tells the agent when this call will succeed versus fail. It does not, however, name the alternative tool to use for Linux servers, leaving that inference to the agent.

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

All Opservo tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?