server_provision

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

Annotations already mark destructiveHint=true, but the description adds critical context: it creates a billable resource, takes 3-5 minutes to initialize, and requires specific environment variables. This goes beyond annotations and helps the agent understand real-world implications.

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 four sentences, each with distinct value: purpose, default, bare mode, prerequisites, warning, and timing. It is front-loaded and compact, with no redundancy.

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 the tool's complexity (6 parameters, multiple providers, modes), the description covers all key behavioral aspects: creation, billing, setup time, prerequisites, and blocking conditions. An output schema exists, so return values need not be described. The description is complete for safe and correct invocation.

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 each parameter is already described. The tool description adds minimal new parameter-specific semantics beyond summarizing defaults and the meaning of mode. Baseline 3 is appropriate as the description does not significantly enhance parameter understanding beyond the schema.

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 'Provision a new server on a cloud provider' and distinguishes default behavior (Coolify) from alternatives ('bare', 'dokploy'). It is specific about the resource created and contrasts with sibling tools like server_audit or server_backup that serve different purposes.

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 context: it requires a provider API token, is blocked when KASTELL_SAFE_MODE=true, and outlines different modes. However, it does not explicitly compare to sibling provisioning tools (none exist) or give when-not-to-use advice beyond the blocking condition.

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