Google Compute Engine

stop_instance

Destructive

Stops a Google Compute Engine virtual machine (VM) instance. Requires project, zone, and instance name as input. Proceed only if there is no error in response and the status of the operation is DONE without any errors. To get details of the operation, use the get_zone_operation tool.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Required. Identifier. The instance name.
`zone`	Yes	Required. The zone of the instance.
`project`	Yes	Required. Project ID for this request.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`operationName`	No	The operation name of the instance stop.

TDQS

A3.9/5.0

Behavior4/5

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

Beyond the annotations (destructiveHint=true, readOnly=false), the description discloses that the operation returns an operation object whose status must be DONE, and directs the agent to get_zone_operation for details. This adds meaningful context about asynchronous behavior and error handling without contradicting the annotations.

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 three sentences, front-loading the purpose and then adding operation-status guidance. The second sentence duplicates schema information somewhat, but the whole is compact and no sentence is wasted.

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 the low complexity, complete schema, and presence of an output schema, the description sufficiently covers the workflow by mentioning the DONE status requirement and pointing to get_zone_operation for follow-up. It does not need to describe return values because an output schema exists.

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 the three parameters are already fully documented. The description only repeats their names ('project, zone, and instance name') without adding value such as format, defaults, or interactions.

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 opens with a specific verb 'Stops' and explicitly names the resource ('Google Compute Engine virtual machine instance'), clearly distinguishing this from sibling tools like start_instance, reset_instance, and delete_instance.

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 implies the use case (stopping a VM) and provides an operational guardrail (wait for DONE status, use get_zone_operation for details), but it does not explicitly state when to choose this over alternatives (e.g., reset vs stop) or include exclusions.

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

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0

Disambiguation5/5

Each tool targets a distinct resource-action combination. For resources with both basic and detailed getters (reservations, templates), the suffixes clearly differentiate them, and list vs get distinctions are unambiguous. No two tools appear to do the same thing.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case (e.g., create_instance, list_disks, get_zone_operation). Getters consistently use descriptive suffixes like basic_info, details, or properties. No mixed naming conventions or vague verbs.

Tool Count4/5

29 tools is slightly above the ideal range but justified given the breadth of Google Compute Engine resources covered (instances, disks, templates, reservations, commitments, MIGs, snapshots, images, machine types, accelerator types). Each tool serves a specific purpose and contributes to the overall scope.

Completeness2/5

The toolset is heavily read-oriented. While instances have full lifecycle coverage (create, delete, start, stop, reset, set machine type), most other resources lack write operations: disks, templates, reservations, commitments, snapshots, and MIGs only have get/list tools. This creates dead ends for agents needing to create or modify these resources, which is a significant gap for a GCE management server.

Resources

Need Help?