Google Compute Engine

list_commitment_reservations

Read-onlyIdempotent

Lists reservations for a Compute Engine Commitment. Returns reservation details including name, ID, status, creation timestamp, specific reservation properties like machine type, guest accelerators and local SSDs, aggregate reservation properties like VM family and reserved resources, commitment and linked commitments, sharing settings, and resource status. Requires project, region, and commitment name as input.

Input Schema

Name	Required	Description
`name`	Yes	Required. Identifier. Name of the commitment to look up reservations for.
`region`	Yes	Required. The region of the commitment.
`project`	Yes	Required. Project ID for this request.

Output Schema

Name	Required	Description	Default
`reservations`	No	The list of reservations.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 10, 2026

changedOutput schema / $defs / UpcomingMaintenance / properties / maintenanceReasons / items / enum

Previous value: -[
-  "FAILURE_DISK",
-  "FAILURE_GPU",
-  "FAILURE_GPU_MULTIPLE_FAULTY_HOSTS_CUSTOMER_REPORTED",
-  "FAILURE_GPU_NVLINK_SWITCH_CUSTOMER_REPORTED",
-  "FAILURE_GPU_TEMPERATURE",
-  "FAILURE_GPU_XID",
-  "FAILURE_INFRA",
-  "FAILURE_INTERFACE",
-  "FAILURE_MEMORY",
-  "FAILURE_NETWORK",
-  "FAILURE_NVLINK",
-  "FAILURE_REDUNDANT_HARDWARE_FAULT",
-  "FAILURE_TPU",
-  "INFRASTRUCTURE_RELOCATION",
-  "MAINTENANCE_REASON_UNKNOWN",
-  "PLANNED_NETWORK_UPDATE",
-  "PLANNED_UPDATE"
-]New value: +[
+  "FAILURE_CUSTOMER_REPORTED",
+  "FAILURE_DISK",
+  "FAILURE_GPU",
+  "FAILURE_GPU_MULTIPLE_FAULTY_HOSTS_CUSTOMER_REPORTED",
+  "FAILURE_GPU_NVLINK_SWITCH_CUSTOMER_REPORTED",
+  "FAILURE_GPU_TEMPERATURE",
+  "FAILURE_GPU_XID",
+  "FAILURE_INFRA",
+  "FAILURE_INTERFACE",
+  "FAILURE_MEMORY",
+  "FAILURE_NETWORK",
+  "FAILURE_NVLINK",
+  "FAILURE_REDUNDANT_HARDWARE_FAULT",
+  "FAILURE_TPU",
+  "INFRASTRUCTURE_RELOCATION",
+  "MAINTENANCE_REASON_UNKNOWN",
+  "PLANNED_NETWORK_UPDATE",
+  "PLANNED_UPDATE"
+]

changedOutput schema / $defs / UpcomingMaintenance / properties / maintenanceReasons / items / x-google-enum-descriptions

Previous value: -[
-  "Maintenance due to disk errors.",
-  "Maintenance due to GPU errors.",
-  "Maintenance due to customer reported multiple faulty hosts via R&R Subblock API.",
-  "Maintenance due to customer reported NVLink switch failure via R&R Subblock API.",
-  "Maintenance due to high GPU temperature.",
-  "Maintenance due to GPU xid failure.",
-  "Maintenance due to infrastructure errors.",
-  "Maintenance due to interface errors.",
-  "Maintenance due to memory errors.",
-  "Maintenance due to network errors.",
-  "Maintenance due to NVLink failure.",
-  "Maintenance due to redundant hardware fault.",
-  "Maintenance due to TPU errors.",
-  "Maintenance due to infrastructure relocation.",
-  "Unknown maintenance reason. Do not use this value.",
-  "Maintenance due to planned network update.",
-  "Maintenance due to planned update to the instance."
-]New value: +[
+  "Maintenance due to a fault reported by the customer via the R&R (Report-and-Replace) API.",
+  "Maintenance due to disk errors.",
+  "Maintenance due to GPU errors.",
+  "Maintenance due to customer reported multiple faulty hosts via R&R Subblock API.",
+  "Maintenance due to customer reported NVLink switch failure via R&R Subblock API.",
+  "Maintenance due to high GPU temperature.",
+  "Maintenance due to GPU xid failure.",
+  "Maintenance due to infrastructure errors.",
+  "Maintenance due to interface errors.",
+  "Maintenance due to memory errors.",
+  "Maintenance due to network errors.",
+  "Maintenance due to NVLink failure.",
+  "Maintenance due to redundant hardware fault.",
+  "Maintenance due to TPU errors.",
+  "Maintenance due to infrastructure relocation.",
+  "Unknown maintenance reason. Do not use this value.",
+  "Maintenance due to planned network update.",
+  "Maintenance due to planned update to the instance."
+]

Changed5 schema fields changedSep 26, 2026

changedOutput schema / $defs / Reservation / properties / aggregateReservation / description

Previous value: -"Reservation for aggregated resources, providing shape flexibility."New value: +"Reservation for aggregated resources, providing shape flexibility. Only one of this field or specificReservation should be set."

changedOutput schema / $defs / Reservation / properties / deleteAfterDuration / description

Previous value: -"Duration time relative to reservation creation when Compute Engine will automatically delete this resource."New value: +"Duration time relative to reservation creation when Compute Engine will automatically delete this resource. Only one of this field or deleteAtTime should be set."

changedOutput schema / $defs / Reservation / properties / deleteAtTime / description

Previous value: -"Absolute time in future when the reservation will be auto-deleted by Compute Engine. Timestamp is represented in RFC3339 <https://www.ietf.org/rfc/rfc3339.txt> text format."New value: +"Absolute time in future when the reservation will be auto-deleted by Compute Engine. Timestamp is represented in RFC3339 <https://www.ietf.org/rfc/rfc3339.txt> text format. Only one of this field or deleteAfterDuration should be set."

changedOutput schema / $defs / Reservation / properties / specificReservation / description

Previous value: -"Reservation for instances with specific machine shapes."New value: +"Reservation for instances with specific machine shapes. Only one of this field or aggregateReservation should be set."

addedOutput schema / $defs / ResourceStatus / properties / machineCount

Added value: +{
+  "description": "The number of machines in the reservation. Only populated for families where machine to host ratio is not 1:1 such as TPU8i.",
+  "format": "int32",
+  "type": "integer"
+}

Changed2 schema fields changedAug 25, 2026

changedOutput schema / $defs / Reservation / properties / confidentialComputeType / enum

Previous value: -[
-  "CONFIDENTIAL_COMPUTE_TYPE_TDX",
-  "CONFIDENTIAL_COMPUTE_TYPE_UNSPECIFIED"
-]New value: +[
+  "CONFIDENTIAL_COMPUTE_TYPE_BMSAI",
+  "CONFIDENTIAL_COMPUTE_TYPE_TDX",
+  "CONFIDENTIAL_COMPUTE_TYPE_UNSPECIFIED"
+]

changedOutput schema / $defs / Reservation / properties / confidentialComputeType / x-google-enum-descriptions

Previous value: -[
-  "Intel Trust Domain Extensions.",
-  ""
-]New value: +[
+  "Bare Metal Secure AI.",
+  "Intel Trust Domain Extensions.",
+  ""
+]

Changed3 schema fields changedApr 6, 2026

addedOutput schema / $defs / Reservation / properties / confidentialComputeType

Added value: +{
+  "enum": [
+    "CONFIDENTIAL_COMPUTE_TYPE_TDX",
+    "CONFIDENTIAL_COMPUTE_TYPE_UNSPECIFIED"
+  ],
+  "type": "string",
+  "x-google-enum-descriptions": [
+    "Intel Trust Domain Extensions.",
+    ""
+  ]
+}

addedOutput schema / $defs / Reservation / properties / resourceMetadata

Added value: +{
+  "$ref": "#/$defs/ResourceMetadata",
+  "description": "Output only. [Output Only] Contains standard resource metadata for an Allocation resource. It is populated for each instance of the Allocation resource, and includes the api_version the instance was retrieved through, and its canonical resource_type name.",
+  "readOnly": true
+}

addedOutput schema / $defs / ResourceMetadata

Added value: +{
+  "description": "Standardized resource metadata common to all compute resources.",
+  "properties": {
+    "apiVersion": {
+      "description": "The version of the API interface that this resource was retrieved through. For example, `\"2025-01-01\"` or `\"2025-01-01-preview\"`.",
+      "type": "string"
+    },
+    "resourceType": {
+      "description": "The canonical resource type name in the format of a resource type as defined by [AIP-123](https://google.aip.dev/123). For example, `\"compute.googleapis.com/Instance\"`.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedMar 30, 2026

removedOutput schema / $defs / Reservation / properties / confidentialComputeType

Removed value: -{
-  "enum": [
-    "CONFIDENTIAL_COMPUTE_TYPE_TDX",
-    "CONFIDENTIAL_COMPUTE_TYPE_UNSPECIFIED"
-  ],
-  "type": "string",
-  "x-google-enum-descriptions": [
-    "Intel Trust Domain Extensions.",
-    ""
-  ]
-}

Changed1 schema field changedMar 26, 2026

addedOutput schema / $defs / Reservation / properties / confidentialComputeType

Added value: +{
+  "enum": [
+    "CONFIDENTIAL_COMPUTE_TYPE_TDX",
+    "CONFIDENTIAL_COMPUTE_TYPE_UNSPECIFIED"
+  ],
+  "type": "string",
+  "x-google-enum-descriptions": [
+    "Intel Trust Domain Extensions.",
+    ""
+  ]
+}

Changed1 schema field changedMar 16, 2026

removedOutput schema / $defs / Reservation / properties / confidentialComputeType

Removed value: -{
-  "enum": [
-    "CONFIDENTIAL_COMPUTE_TYPE_TDX",
-    "CONFIDENTIAL_COMPUTE_TYPE_UNSPECIFIED"
-  ],
-  "type": "string",
-  "x-google-enum-descriptions": [
-    "Intel Trust Domain Extensions.",
-    ""
-  ]
-}

Changed1 schema field changedMar 13, 2026

addedOutput schema / $defs / Reservation / properties / confidentialComputeType

Added value: +{
+  "enum": [
+    "CONFIDENTIAL_COMPUTE_TYPE_TDX",
+    "CONFIDENTIAL_COMPUTE_TYPE_UNSPECIFIED"
+  ],
+  "type": "string",
+  "x-google-enum-descriptions": [
+    "Intel Trust Domain Extensions.",
+    ""
+  ]
+}

First observedFeb 23, 2026

TDQS

B3.4/5.0

Behavior3/5

Does 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. What remains is a long enumeration of returned fields, which largely duplicates the output schema rather than adding new behavioral context (pagination, rate limits, auth requirements).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded, but the middle of the description is a lengthy field-by-field enumeration of return values that is largely redundant given the output schema. It would be tighter if it dropped the return-field list.

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 an output schema present and annotations covering safety, the description only needs to convey scope and inputs, which it does. The scoping to a commitment and the required inputs make it callable without opening the schema, leaving little materially missing.

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% and all three parameters are documented in the schema itself. The description restates project, region, and commitment name without adding syntax, format, or fallback meaning, so it does no work beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Lists reservations for a Compute Engine Commitment'), which scopes it apart from the broader 'list_reservations' sibling. However, it never explicitly contrasts itself with that sibling, so the differentiation is implied rather than stated.

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

Usage Guidelines3/5

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

The description notes the required inputs ('Requires project, region, and commitment name as input'), which implies the usage context of looking up reservations scoped to a single commitment. It gives no explicit when-to-use guidance and never names 'list_reservations' or 'get_reservation_details' as alternatives.

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

All Google Compute Engine 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?