workspace-listList currently loaded workspaces to identify open solutions or projects before applying Roslyn code actions.
Lists the currently loaded workspaces.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.4Output schema / (root)Previous value: -nullNew value: +{
+ "$defs": {
+ "warningInfo": {
+ "properties": {
+ "code": {
+ "description": "The stable machine-readable warning code.",
+ "type": "string"
+ },
+ "message": {
+ "description": "The human-readable warning message.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+ }
+ },
+ "oneOf": [
+ {
+ "properties": {
+ "data": {
+ "description": "Tool-specific result payload.",
+ "properties": {
+ "transactionOwnerWorkspaceId": {
+ "description": "The workspace identifier that currently owns the global transaction slot, when present.",
+ "format": "uuid",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "workspaces": {
+ "description": "The loaded workspaces.",
+ "items": {
+ "properties": {
+ "alias": {
+ "description": "The optional caller-friendly alias.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "loadedPath": {
+ "description": "The absolute path of the loaded workspace.",
+ "type": "string"
+ },
+ "workspaceEpoch": {
+ "description": "The workspace epoch for the loaded baseline.",
+ "type": "integer"
+ },
+ "workspaceId": {
+ "description": "The stable server-generated workspace identifier.",
+ "format": "uuid",
+ "type": "string"
+ },
+ "workspaceRoot": {
+ "description": "The absolute repository or workspace root used for coordination and transaction boundaries.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "loadedPath",
+ "workspaceRoot"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "type": [
+ "object",
+ "null"
+ ]
+ },
+ "ok": {
+ "const": true,
+ "description": "Whether the tool invocation succeeded."
+ },
+ "snapshot": {
+ "description": "Exact immutable workspace snapshot associated with the result, when available.",
+ "properties": {
+ "snapshotId": {
+ "format": "uuid",
+ "type": "string"
+ },
+ "transactionRevision": {
+ "type": [
+ "integer",
+ "null"
+ ]
+ },
+ "workspaceEpoch": {
+ "type": "integer"
+ },
+ "workspaceId": {
+ "format": "uuid",
+ "type": "string"
+ }
+ },
+ "required": [
+ "workspaceId",
+ "workspaceEpoch",
+ "snapshotId",
+ "transactionRevision"
+ ],
+ "type": "object"
+ },
+ "warnings": {
+ "description": "Non-fatal warnings the agent should consider.",
+ "items": {
+ "$ref": "#/$defs/warningInfo"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "ok",
+ "data"
+ ],
+ "type": "object"
+ },
+ {
+ "properties": {
+ "continuation": {
+ "description": "Action the agent should take before retrying or continuing.",
+ "oneOf": [
+ {
+ "additionalProperties": false,
+ "properties": {
+ "instruction": {
+ "description": "Agent-facing instruction explaining how to continue.",
+ "minLength": 1,
+ "type": "string"
+ },
+ "kind": {
+ "const": "CallTool",
+ "description": "Action required before the original request can continue."
+ },
+ "tool": {
+ "description": "Tool to call before continuing the original request.",
+ "minLength": 1,
+ "type": "string"
+ }
+ },
+ "required": [
+ "kind",
+ "tool",
+ "instruction"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "instruction": {
+ "description": "Agent-facing instruction explaining how to continue.",
+ "minLength": 1,
+ "type": "string"
+ },
+ "kind": {
+ "const": "ChooseTool",
+ "description": "Action required before the original request can continue."
+ },
+ "tools": {
+ "description": "Allowed tool choices from which the agent must select one.",
+ "items": {
+ "description": "Name of a tool the agent may choose.",
+ "minLength": 1,
+ "type": "string"
+ },
+ "minItems": 1,
+ "type": "array",
+ "uniqueItems": true
+ }
+ },
+ "required": [
+ "kind",
+ "tools",
+ "instruction"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "instruction": {
+ "description": "Agent-facing instruction explaining how to continue.",
+ "minLength": 1,
+ "type": "string"
+ },
+ "kind": {
+ "const": "RetryRequest",
+ "description": "Action required before the original request can continue."
+ }
+ },
+ "required": [
+ "kind",
+ "instruction"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "instruction": {
+ "description": "Agent-facing instruction explaining how to continue.",
+ "minLength": 1,
+ "type": "string"
+ },
+ "kind": {
+ "const": "ReviseRequest",
+ "description": "Action required before the original request can continue."
+ }
+ },
+ "required": [
+ "kind",
+ "instruction"
+ ],
+ "type": "object"
+ },
+ {
+ "additionalProperties": false,
+ "properties": {
+ "instruction": {
+ "description": "Agent-facing instruction explaining how to continue.",
+ "minLength": 1,
+ "type": "string"
+ },
+ "kind": {
+ "const": "ResolveExternally",
+ "description": "Action required before the original request can continue."
+ }
+ },
+ "required": [
+ "kind",
+ "instruction"
+ ],
+ "type": "object"
+ }
+ ]
+ },
+ "diagnostics": {
+ "description": "Diagnostics that explain the failed invocation.",
+ "items": {
+ "properties": {
+ "id": {
+ "description": "The diagnostic identifier.",
+ "type": "string"
+ },
+ "location": {
+ "description": "The optional source location of the diagnostic.",
+ "properties": {
+ "column": {
+ "description": "The one-based column number.",
+ "type": "integer"
+ },
+ "document": {
+ "description": "The resolved document.",
+ "properties": {
+ "documentId": {
+ "description": "The document identifier.",
+ "type": "string"
+ },
+ "path": {
+ "description": "The normalized document path.",
+ "type": "string"
+ },
+ "projectId": {
+ "description": "The owning project identifier.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "documentId",
+ "path",
+ "projectId"
+ ],
+ "type": [
+ "object",
+ "null"
+ ]
+ },
+ "line": {
+ "description": "The one-based line number.",
+ "type": "integer"
+ },
+ "selector": {
+ "description": "The canonical selector that can resolve this source location again.",
+ "properties": {
+ "span": {
+ "properties": {
+ "document": {
+ "description": "Provide exactly one of path or documentId.",
+ "properties": {
+ "documentId": {
+ "description": "Workspace-local document ID.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "path": {
+ "description": "Workspace-relative path.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "project": {
+ "description": "Disambiguates documents with matching paths or IDs.",
+ "properties": {
+ "name": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "path": {
+ "description": "Workspace-relative path.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "projectId": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "targetFramework": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": [
+ "object",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ "range": {
+ "description": "Zero-based UTF-16 range.",
+ "properties": {
+ "length": {
+ "description": "UTF-16 code-unit length.",
+ "maximum": 2147483647,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "start": {
+ "description": "Zero-based UTF-16 offset.",
+ "maximum": 2147483647,
+ "minimum": 0,
+ "type": "integer"
+ }
+ },
+ "type": "object"
+ }
+ },
+ "required": [
+ "document",
+ "range"
+ ],
+ "type": "object"
+ }
+ },
+ "required": [
+ "span"
+ ],
+ "type": [
+ "object",
+ "null"
+ ]
+ },
+ "snapshot": {
+ "description": "The exact immutable workspace snapshot associated with this location.",
+ "properties": {
+ "snapshotId": {
+ "format": "uuid",
+ "type": "string"
+ },
+ "transactionRevision": {
+ "type": [
+ "integer",
+ "null"
+ ]
+ },
+ "workspaceEpoch": {
+ "type": "integer"
+ },
+ "workspaceId": {
+ "format": "uuid",
+ "type": "string"
+ }
+ },
+ "required": [
+ "workspaceId",
+ "workspaceEpoch",
+ "snapshotId",
+ "transactionRevision"
+ ],
+ "type": "object"
+ },
+ "span": {
+ "description": "The resolved text span.",
+ "properties": {
+ "length": {
+ "description": "UTF-16 code-unit length.",
+ "maximum": 2147483647,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "start": {
+ "description": "Zero-based UTF-16 offset.",
+ "maximum": 2147483647,
+ "minimum": 0,
+ "type": "integer"
+ }
+ },
+ "type": [
+ "object",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "snapshot"
+ ],
+ "type": [
+ "object",
+ "null"
+ ]
+ },
+ "message": {
+ "description": "The diagnostic message.",
+ "type": "string"
+ },
+ "severity": {
+ "description": "The diagnostic severity.",
+ "enum": [
+ "Hidden",
+ "Info",
+ "Warning",
+ "Error"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "message"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "error": {
+ "description": "Structured error details when the invocation failed.",
+ "properties": {
+ "code": {
+ "description": "Stable machine-readable error code.",
+ "type": "string"
+ },
+ "correlationId": {
+ "description": "Correlation identifier for matching the failure to server-side diagnostics, when available.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "message": {
+ "description": "Human-readable explanation of the failure.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "code",
+ "message"
+ ],
+ "type": "object"
+ },
+ "ok": {
+ "const": false,
+ "description": "Whether the tool invocation succeeded."
+ },
+ "warnings": {
+ "description": "Non-fatal warnings the agent should consider.",
+ "items": {
+ "$ref": "#/$defs/warningInfo"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "ok",
+ "error"
+ ],
+ "type": "object"
+ },
+ {
+ "properties": {
+ "diagnostics": {
+ "description": "Diagnostics that explain the failed invocation.",
+ "properties": {
+ "detailsAvailable": {
+ "const": true
+ },
+ "detailsTool": {
+ "const": "get-error-details"
+ }
+ },
+ "required": [
+ "detailsAvailable",
+ "detailsTool"
+ ],
+ "type": "object"
+ },
+ "error": {
+ "description": "Structured error details when the invocation failed.",
+ "properties": {
+ "code": {
+ "const": "UnhandledException"
+ },
+ "correlationId": {
+ "format": "uuid",
+ "type": "string"
+ },
+ "message": {
+ "const": "Tool execution failed."
+ }
+ },
+ "required": [
+ "code",
+ "message",
+ "correlationId"
+ ],
+ "type": "object"
+ },
+ "ok": {
+ "const": false,
+ "description": "Whether the tool invocation succeeded."
+ },
+ "reporting": {
+ "description": "Error-reporting workflow available for an unhandled failure.",
+ "properties": {
+ "canPrepare": {
+ "type": "boolean"
+ },
+ "prepareTool": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "state": {
+ "enum": [
+ "Available",
+ "AlwaysApproved",
+ "DisabledByConfiguration",
+ "ApprovalUnavailable"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "state"
+ ],
+ "type": "object"
+ }
+ },
+ "required": [
+ "ok",
+ "error",
+ "diagnostics"
+ ],
+ "type": "object"
+ }
+ ],
+ "type": "object"
+}v1.0.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds only that it returns 'currently loaded' workspaces rather than all known ones, which is useful scoping but thin given the annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One short sentence with the scope qualifier front-loaded and no wasted words. Perfectly sized for a parameterless list operation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, return values need not be described, and the read-only annotations cover behavior. The only missing piece is routing guidance against the many workspace-* siblings, which is minor for such a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline of 4 applies for a parameterless tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Lists') and resource ('workspaces') with the qualifier 'currently loaded'. An agent can tell it apart from workspace-open/close/reload, though it does not distinguish itself from the adjacent workspace-status tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no when-to-use guidance, no prerequisites, and never mentions the sibling tools (workspace-open, workspace-status) that an agent would need to choose between. Usage must be entirely inferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.