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

Annotations already declare write, idempotent, open-world, and non-destructive behavior. The description adds meaningful context beyond that: credit is spent or an invoice is raised, a provisioning action is returned, retries are deduplicated for 24 hours, and the required scope is vms.create.

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 short, front-loaded with the core action, and each sentence adds useful information about billing, return value, idempotency, or scope. There is no wasted text.

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 complex 13-parameter mutation with no output schema, the description covers the important missing context: what it returns, how to poll the provisioning action, billing implications, retry safety, and the permission scope. Remaining parameter details are fully covered by the schema.

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 description coverage is 100%, so the parameters are already well documented. The description reinforces billing behavior but does not add syntax or meaning beyond the schema for the 13 parameters, so the baseline score applies.

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 uses a specific verb and resource: it orders a machine, states the billing effect, and says it returns the machine plus a provisioning action. It is clear what the tool does, though it does not explicitly distinguish itself from the sibling estimate_vm 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?

It provides usage context by saying the retry is deduplicated for 24 hours and that the returned action should be polled with get_action. However, it does not explicitly say when to use create_vm instead of estimate_vm or list the prerequisite discovery tools, leaving alternatives mostly implied.

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