Skip to main content
Glama
Sign In

Opsphere — DevOps & SRE Intelligence

by io.opsphere.mcp-cursor
OverviewDiscussionsAdmin

kubectl describe

k8s_describe
Read-only

Describe a Kubernetes resource in detail (read-only). Shows configuration, status, events and metadata. Useful for understanding why a pod is not starting, verifying deployment configurations, reviewing services and analyzing nodes. IMPORTANT: If looking for a cronjob and want to see its pods, first use k8s.pods.list or k8s.cronjob.pods to find the related pods. Examples: "describe the storefront deployment in production", "describe the failing pod", "describe the contentful-import cronjob".

Input Schema

NameRequiredDescriptionDefault
nsNoNamespace; alias: namespace
kindNoResource kind, e.g. deployment, externalsecret, service, pod
nameNoResource name
contextNokubectl --context opcional
profileNoAWS_PROFILE opcional para EKS/SSO
resourceNoAlternative kind/name form, e.g. externalsecret/sfdc
namespaceNoAlias of ns
context_idNoOptional explicit Connection Hub work context (ctx_*). Omit to use the conversation's active workspace; global Hub tools ignore it.
environment_slugNoCloud catalog environment slug or alias (resolves AWS profile and kubectl context)

Output Schema

NameRequiredDescriptionDefault
okYes
dataYes
contractVersionYes
dataSchemaVersionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changed
    • addedOutput schema / properties / data / properties / conditions
      Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "lastTransitionAt": {
+        "$ref": "#/properties/data/properties/observedAt"
+      },
+      "message": {
+        "type": "string"
+      },
+      "reason": {
+        "type": "string"
+      },
+      "status": {
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "status"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / data / properties / events
      Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "count": {
+        "minimum": 0,
+        "type": "integer"
+      },
+      "firstSeenAt": {
+        "$ref": "#/properties/data/properties/observedAt"
+      },
+      "lastSeenAt": {
+        "$ref": "#/properties/data/properties/observedAt"
+      },
+      "message": {
+        "type": "string"
+      },
+      "reason": {
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "message"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • removedOutput schema / properties / data / properties / format
      Removed value: -{
-  "enum": [
-    "plain",
-    "markdown",
-    "json"
-  ],
-  "type": "string"
-}
    • addedOutput schema / properties / data / properties / gaps
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / data / properties / observedAt
      Added value: +{
+  "format": "date-time",
+  "type": "string"
+}
    • addedOutput schema / properties / data / properties / partial
      Added value: +{
+  "type": "boolean"
+}
    • addedOutput schema / properties / data / properties / resource
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "account": {
+      "type": "string"
+    },
+    "environment": {
+      "type": "string"
+    },
+    "id": {
+      "type": "string"
+    },
+    "name": {
+      "type": "string"
+    },
+    "provider": {
+      "type": "string"
+    },
+    "type": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "provider",
+    "type",
+    "id",
+    "name"
+  ],
+  "type": "object"
+}
    • addedOutput schema / properties / data / properties / statusSummary
      Added value: +{
+  "type": "string"
+}
    • removedOutput schema / properties / data / properties / text
      Removed value: -{
-  "type": "string"
-}
    • addedOutput schema / properties / data / properties / truncated
      Added value: +{
+  "type": "boolean"
+}
    • addedOutput schema / properties / data / properties / warnings
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / data / properties / yaml
      Added value: +{
+  "type": "string"
+}
    • changedOutput schema / properties / data / required
      Previous value: -[
-  "text"
-]New value: +[
+  "resource",
+  "observedAt",
+  "yaml",
+  "conditions",
+  "events",
+  "partial",
+  "truncated",
+  "warnings",
+  "gaps"
+]
    • addedOutput schema / properties / dataSchemaVersion
      Added value: +{
+  "const": 2,
+  "type": "number"
+}
    • changedOutput schema / required
      Previous value: -[
-  "contractVersion",
-  "ok",
-  "data"
-]New value: +[
+  "contractVersion",
+  "dataSchemaVersion",
+  "ok",
+  "data"
+]
  2. First observed

TDQS

A4.1/5.0
Behavior3/5

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

The '(read-only)' parenthetical only restates readOnlyHint=true and destructiveHint=false, earning no extra credit. What it does add is that output includes status, events, and metadata, which helps an agent know this is the diagnostic surface rather than a list. It says nothing about permissions, latency, or size of output for large resources, so it stays at a solid but not rich 3.

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-loads the definition, then use cases, then the critical routing caveat, then examples — a good information order with little waste. It runs slightly long, and the routing note could be trimmed, but every block contributes.

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

Completeness4/5

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

With nine optional parameters, an output schema, and annotations already covering safety, the description supplies what's missing: what the output contains and when to prefer other tools. The one residual gap is guidance on choosing among the overlapping namespace/kind-name/resource parameter shapes, which the schema handles only mechanically.

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?

Schema coverage is 100%, so all nine parameters are already documented, and this tool is at the baseline. The examples implicitly show kind+name usage, but the description never explains how kind/name relates to the alternative 'resource' form, nor what profile/environment_slug/context_id do beyond the schema text.

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 ('Describe a Kubernetes resource in detail'), enumerates what is returned (configuration, status, events, metadata), and is clearly separable from siblings like k8s_find_pod, k8s_cluster_summary, and k8s_cronjob_pods. The natural-language examples further anchor the operation.

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

Usage Guidelines5/5

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

Gives explicit use cases (pod not starting, verifying deployment configs, reviewing services, analyzing nodes) and an IMPORTANT routing rule: for cronjob pods use k8s.pods.list or k8s.cronjob.pods first. That is when-to-use plus a named alternative, which is the top of the scale.

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

All Opsphere — DevOps & SRE Intelligence toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources