resize_disk

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

With no annotations provided, the description carries the full burden. It explicitly labels the operation as DESTRUCTIVE, states the VM must be stopped, and notes that shrinking is not possible. It also discloses that confirm=true is required to execute and that otherwise a preview is returned. This goes beyond simple safety labeling and gives meaningful behavioral expectations.

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 compact and well-structured. It leads with a bold purpose statement, follows with a short precondition sentence, and lists arguments in a clear block. Every sentence carries essential information, and the formatting improves scannability without unnecessary verbosity.

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?

For a destructive operation with no annotations, the description covers all essential context: destructive nature, preconditions (stopped VM), constraints (expand-only), and the preview/confirm workflow. The output schema exists to handle return details, so no additional output explanation is needed. This is a complete and self-sufficient description.

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 schema has 0% description coverage, yet the description fully compensates by enumerating each argument with clear explanations: vm_id, disk_id (with source reference), size_gb (with units), and confirm (with behavior). This provides all necessary semantic meaning beyond the raw schema types, making parameter usage unambiguous.

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 begins with 'DESTRUCTIVE: Resize a virtual disk (expand only).' This clearly states the specific action (resize), the resource (virtual disk), and the critical constraint (expand only). It distinguishes from sibling tools like delete_disk or create_vm, and leaves no ambiguity about the tool's function.

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 provides the key prerequisite 'The VM should be stopped' and the expansion limitation. It also points to list_vm_disks as the source for disk_id, giving contextual guidance. While it doesn't name alternative tools (there are none for resizing), it clearly implies when to use this tool: after stopping the VM and only to increase disk size. A slight addition of explicit 'when not to use' would earn a 5.

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