create_server

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

With no annotations at all, the description carries the full burden and does meaningful work: it discloses billing behavior (first 30 days charged from account balance), latency (setup takes minutes), the OS restriction, the one-time root password reveal when ssh_keys is omitted, and the required scope servers:create. It does not say whether the order is cancellable/refundable or what the response contains, which keeps it from a 5.

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?

Five short sentences, zero filler, with the core action and the server/shared distinction front-loaded before the operational caveats. Every clause (billing, timing, OS, password, scope) supplies information an agent needs.

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 9-parameter, no-annotation, no-output-schema mutation tool this is close to sufficient: cost, latency, OS limit, credential behavior and required scope are all covered. The remaining gap is the return value — the description only implies an order is created that get_order can look up, without saying what identifier comes back.

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 baseline is 3; the description earns above that by explaining the kind enum in business terms (server = own root server) and by describing the conditional behavior tied to ssh_keys (no keys → one-time root password). The noroot/confirm_no_root coupling is restated from the schema rather than extended, so it is not a full 5.

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?

Opens with a specific verb and resource ("Order a server ... or a shared account") and immediately disambiguates the two modes via the kind enum. It also names the sibling tools (get_order, get_server) used to follow progress, so an agent can place it among the 19 siblings without opening a schema.

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 states the operational context (setup takes a few minutes, watch it with get_order or get_server) and the hard constraint (Ubuntu 24.04 only), which tells the agent when this tool applies and what to do right after calling it. It stops short of explicit prerequisites like "call list_plans first to get plan/region ids" and offers no when-not-to-use exclusion, leaving that to the schema.

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