Purchase new virtual machine

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

Annotations provide readOnlyHint=false and destructiveHint=false, which only indicate it is a mutating (write) operation but not destructive in a harmful sense. The description goes beyond annotations by disclosing important behavioral traits: it details what happens on setup failure (manual completion required), the automatic default payment method if none is provided, and the meaning of the 202 Accepted response (payment still processing, VM not set up). This gives the agent critical operational context, though it doesn't specifcy exact side effects like billing charges or irreversible actions, but the provided information is substantial.

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 concise (about 6 sentences) and front-loaded with the main purpose. It uses bullet-like paragraphs for clarity, but it includes a hyperlink URL for hPanel which is not essential to the description's semantics (though it may be useful for the agent to provide to the user). The information is relevant and no filler words, but could be slightly more compact while retaining key details.

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 that the tool has no output schema, the description thoroughly covers the critical execution outcomes: success, failure handling, and asynchronous processing (202). It adequately explains the use of parameters and the fallback behavior. It does not explicitly list prerequisites (e.g., need to browse catalog first), but that is inferable. Overall, it is complete enough for the agent to understand invocation and post-call steps, though it could mention that the 'setup' parameter is required for configuration details.

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 input schema has 100% description coverage, meaning each parameter has a description (e.g., 'setup parameter', 'Discount coupon codes', 'Catalog price item ID', 'Payment method ID, default will be used if not provided'). The description adds value by clarifying the payment_method_id default behavior and implying that item_id comes from the catalog. However, the description does not elaborate on the 'setup' parameter or 'coupons' beyond their schema descriptions, but given high schema coverage, this is adequate.

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 clearly states the tool's purpose: 'Purchase and setup a new virtual machine.' with a specific verb (purchase/setup) and resource (virtual machine). It also clarifies 'Use this endpoint to create new VPS instances,' which distinguishes it from other VPS management tools (e.g., VPS_getVirtualMachinesV1, VPS_startVirtualMachineV1). The title and description align, and the scope is unambiguous.

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 explicit usage context: it explains when to use this tool (to create new VPS instances) and includes crucial guidance on failure handling (login to hPanel if setup fails). It also clarifies payment behavior (default payment method if not provided) and the meaning of a 202 response, which tells the agent when manual intervention is needed. It doesn't name alternatives explicitly, but given the sibling list, the purpose is distinct enough; and the failure-contingency guidance is strong.

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