Opsphere — DevOps & SRE Intelligence

EKS update-kubeconfig

eks_update_kubeconfig

Sensitive setup action: update/create the default kubeconfig entry for an EKS cluster. Requires you to already KNOW the cluster name. Do not use this for health checks or other read-only monitoring: Kubernetes tools accept profile and context directly and create isolated runtime access. DO NOT use this to discover clusters — use k8s_contexts to list available clusters/contexts, or eks_sync_cluster_metadata to discover clusters from the AWS account.

Input Schema

Name	Required	Description
`alias`	No	Alias de contexto opcional
`region`	Yes	Región, p.ej. eu-central-1
`profile`	No	AWS_PROFILE opcional
`context_id`	No	Optional explicit Connection Hub work context (ctx_*). Omit to use the conversation's active workspace; global Hub tools ignore it.
`clusterName`	Yes	Nombre del cluster EKS

Output Schema

Name	Required	Description	Default
`ok`	Yes
`data`	Yes
`contractVersion`	Yes
`dataSchemaVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedOct 26, 2026

changedOutput schema / properties / data / additionalProperties
```
Previous value: -trueNew value: +false
```
removedOutput schema / properties / data / properties / apiVersion
```
Removed value: -{
-  "type": "string"
-}
```
addedOutput schema / properties / data / properties / cluster
```
Added value: +{
+  "type": "string"
+}
```
removedOutput schema / properties / data / properties / count
```
Removed value: -{
-  "type": "number"
-}
```

addedOutput schema / properties / data / properties / gaps

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

removedOutput schema / properties / data / properties / items

Removed value: -{
-  "items": {
-    "additionalProperties": true,
-    "properties": {},
-    "type": "object"
-  },
-  "type": "array"
-}

removedOutput schema / properties / data / properties / kind
```
Removed value: -{
-  "type": "string"
-}
```

removedOutput schema / properties / data / properties / metadata

Removed value: -{
-  "$ref": "#/properties/data/properties/items/items"
-}

removedOutput schema / properties / data / properties / namespace
```
Removed value: -{
-  "type": "string"
-}
```
addedOutput schema / properties / data / properties / partial
```
Added value: +{
+  "type": "boolean"
+}
```

removedOutput schema / properties / data / properties / status

Removed value: -{
-  "$ref": "#/properties/data/properties/items/items"
-}

addedOutput schema / properties / data / properties / truncated
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / data / properties / updated
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / data / properties / warnings

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / data / required

Added value: +[
+  "context",
+  "cluster",
+  "updated",
+  "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"
+]

First observedOct 15, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-open-world. The description adds real value on top: it writes into the default kubeconfig entry (a local, persistent side effect), it is a 'sensitive setup action', and Kubernetes tools can bypass it by passing profile/context directly. It stops short of saying what happens to an existing entry (overwrite vs. merge) or whether auth is required.

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 action and its sensitivity, then the exclusions and alternatives. Slightly verbose with heavy capitalization for emphasis, but every sentence carries routing or precondition information.

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?

Given an output schema exists and annotations cover the safety profile, the description supplies the missing decision context (when not to use, what to use instead) and the known-cluster-name precondition. Only the overwrite semantics of the default kubeconfig entry are left unstated.

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 description coverage is 100%, so region, clusterName, profile, alias, and context_id are already documented. The description only reinforces that clusterName must be known in advance; it adds no format or interaction detail for the other four parameters. Baseline 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+resource ('update/create the default kubeconfig entry for an EKS cluster') and immediately distinguishes it from read-only monitoring and cluster-discovery siblings. An agent can place it precisely without opening the schema.

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?

Explicitly names when NOT to use it (health checks, read-only monitoring, cluster discovery) and routes to concrete alternatives: k8s_contexts for listing contexts and eks_sync_cluster_metadata for AWS-side discovery. Also flags the precondition that the cluster name must already be known.

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 tools Inspect

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

Need Help?