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

Annotations already indicate this is a write operation (readOnlyHint=false) with destructive potential (destructiveHint=true). The description adds useful behavioral context by explaining the asynchronous operation monitoring: check for errors and wait for status DONE, and use get_zone_operation for details. It also reveals default image and machine type behavior, which is not discoverable from the schema alone. It does not contradict 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.

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

The description is efficiently structured: purpose first, then requirements, defaults, optional parameters, and finally success criteria. It is somewhat long, and the phrase 'without any errors' is redundant, but every sentence contributes actionable information. The front-loaded purpose makes it easy to scan quickly.

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?

Given the rich annotations, complete schema coverage, and the presence of an output schema, the description covers essential operational details: prerequisites, default values, optional configuration, and how to verify a successful operation via get_zone_operation. No critical information is missing for an agent to safely invoke the 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?

Schema coverage is 100%, so the schema documents all parameters, but the description adds value by specifying defaults for machineType and imageProject/imageFamily, and by naming guestAccelerators and maintenancePolicy as optional. It uses slightly different parameter names ('guest_accelerator' vs 'guestAccelerators'), which is a minor inconsistency, but the overall meaning is still conveyed.

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?

The description opens with a specific verb and resource: 'Create a new Google Compute Engine virtual machine (VM) instance.' This clearly distinguishes create_instance from sibling tools like delete_instance, reset_instance, or start_instance. It also lists required parameters, making the tool's scope immediately obvious.

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 gives practical context: required inputs (project, zone, name), default machine type and image, and optional parameters. It also instructs the agent to check the operation status and references get_zone_operation. It does not explicitly state exclusions or when to prefer alternatives, but the create/delete/update sibling set makes the use case clear.

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