Opsphere — DevOps & SRE Intelligence

Switch active workspace (confirmation required)

ops_context_open

Destructive

Connection Hub only. Persistently select a linked workspace, atomically replacing and closing the previous active context and updating the client preference. This is never a temporary switch. Call only after the user explicitly asks to switch to the named workspace or explicitly confirms a proposed switch. A request for a ticket, zone, repository, project, provider, or tool that belongs to another workspace is not confirmation: explain the mismatch and ask first. Never switch to answer and then switch back automatically. Returns context_id, expires_at, conversation_scope, and replaced_context_ids. Optional chat_session_key is a stable host-supplied conversation identity; never invent one. Without it, the MCP gateway session is the scope.

Input Schema

Name	Required	Description	Default
`chat_session_key`	No
`linked_connection_id`	Yes

Output Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 27, 2026

changedOutput schema / properties / data / properties / accounts / items / additionalProperties

Previous value: -{
-  "type": [
-    "string",
-    "number",
-    "boolean",
-    "null"
-  ]
-}New value: +false

addedOutput schema / properties / data / properties / accounts / items / properties

Added value: +{
+  "display_name": {
+    "type": "string"
+  },
+  "id": {
+    "type": "string"
+  },
+  "label": {
+    "type": "string"
+  },
+  "linked_at": {
+    "type": "string"
+  },
+  "status": {
+    "type": "string"
+  },
+  "tenant": {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "slug": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "required": [
+      "id",
+      "slug"
+    ],
+    "type": "object"
+  }
+}

addedOutput schema / properties / data / properties / accounts / items / required

Added value: +[
+  "id",
+  "label",
+  "tenant",
+  "status",
+  "display_name",
+  "linked_at"
+]

removedOutput schema / properties / data / properties / connections / $ref
```
Removed value: -"#/properties/data/properties/accounts"
```

addedOutput schema / properties / data / properties / connections / items

Added value: +{
+  "$ref": "#/properties/data/properties/accounts/items"
+}

addedOutput schema / properties / data / properties / connections / type
```
Added value: +"array"
```

changedOutput schema / properties / data / properties / error / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "$ref": "#/properties/data/properties/accounts/items"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": {
+      "type": [
+        "string",
+        "number",
+        "boolean",
+        "null"
+      ]
+    },
+    "type": "object"
+  }
+]

Changed6 schema fields changedOct 26, 2026

changedOutput schema / properties / data / additionalProperties
```
Previous value: -trueNew value: +false
```

changedOutput schema / properties / data / properties / accounts / items / additionalProperties

Previous value: -trueNew value: +{
+  "type": [
+    "string",
+    "number",
+    "boolean",
+    "null"
+  ]
+}

removedOutput schema / properties / data / properties / accounts / items / properties
```
Removed value: -{}
```

addedOutput schema / properties / data / properties / connection

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "display_name": {
+      "type": "string"
+    },
+    "tenant_id": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / dataSchemaVersion

Added value: +{
+  "const": 1,
+  "type": "number"
+}

changedOutput schema / required

Previous value: -[
-  "contractVersion",
-  "ok",
-  "data"
-]New value: +[
+  "contractVersion",
+  "dataSchemaVersion",
+  "ok",
+  "data"
+]

First observedOct 15, 2026

TDQS

A4.5/5.0

Behavior5/5

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

The annotations already mark this as destructive, and the description adds substantial context beyond them: it destroys/replaces the previous active context, updates the client preference, is never temporary, and must not be auto-reversed. It also discloses return fields and the identity semantics of chat_session_key, which are not captured by the annotations alone.

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 action and scope, and most sentences carry high-value behavioral or usage constraints. The sentence listing return values is somewhat redundant because an output schema exists, making the description slightly longer than strictly necessary.

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?

For a destructive context-switch tool, it covers purpose, usage constraints, destruction semantics, and return behavior well, and annotations plus output schema carry the safety and return-shape load. The main remaining gap is that it does not tell an agent where to obtain the required linked_connection_id.

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 0%, so the description must carry parameter meaning. It thoroughly explains the optional chat_session_key (stable host-supplied conversation identity; never invent one; gateway session is used without it), but linked_connection_id is only indirectly described as selecting a 'linked workspace' or 'named workspace' with no format, source, or example for obtaining a valid ID.

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 states a specific action: persistently select and activate a linked workspace in Connection Hub, atomically replacing the previous context. It explicitly distinguishes this from a temporary switch and scopes the tool to Connection Hub only, so an agent can tell what it does and what it is not.

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?

It gives explicit when-to-use conditions (only after the user explicitly asks or explicitly confirms a proposed switch) and concrete exclusions (a request for a ticket, zone, repository, project, provider, or tool in another workspace is not confirmation). It also provides behavioral alternatives: explain the mismatch and ask first, and never switch to answer then switch back automatically.

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?