createVhost

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

With no annotations, the description carries the burden of revealing behavior. It discloses that service_handle is auto-assigned (not user-set) and that only default on-aptible.com domains are supported, which is useful. However, it omits details about side effects (e.g., provisioning time, whether it triggers a deploy), required permissions, or how conflicts (e.g., existing vhost) are handled, so transparency is partial.

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 has a clear lead sentence but includes extraneous content such as a TODO note ('Add support for database endpoints and custom endpoints') and a conversational aside ('Since this is being used by AI, that shouldn't matter, though.'). These could be removed or condensed to improve focus, though the description remains moderately concise.

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?

The description covers key limits (services only, default domains) and mentions the service_handle peculiarity, but it does not state prerequisites (e.g., app/service must exist) or expected behavior after creation. While an output schema exists (which may describe return values), the description still lacks important context for a create operation, leaving moderate gaps.

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 provides zero parameter descriptions, so the description must compensate. It explains the service_handle quirk (auto-assigned by Aptible, mapped via process_type) but does not explain account_handle at all, and it only indirectly references app_handle. With 3 parameters and 0% coverage, this is insufficient for an agent to understand all inputs.

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 'Create a new vhost/endpoint for a Service,' which clearly states the verb ('create'), the resource ('vhost/endpoint'), and the scope ('for a Service'). This distinguishes it from sibling tools like listVhosts, deleteVhost, and createDatabase, making the purpose 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 context on when this tool is appropriate: it only supports default on-aptible.com domains for Services, explicitly noting that database endpoints and custom endpoints are not yet supported. While it doesn't name alternative tools, these constraints clearly signal when not to use it and guide the agent toward appropriate use cases.

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