server_maintain

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

The description adds some behavioral context (SSH vs API tokens, server types) but contradicts the input schema regarding supported platforms ('Coolify only' vs 'Coolify or Dokploy'). Annotations indicate idempotentHint=true, but actions like restart and maintain involve rebooting, which may not be strictly idempotent. The description does not clarify this inconsistency, potentially misleading the agent.

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 a single paragraph that front-loads the main actions then states requirements and limitations. It is efficient but could be slightly more structured (e.g., bullet points) for easier parsing. However, it remains concise and readable.

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 (three actions, server types, prerequisites), the description covers many aspects but misses some details: it does not explain the 5-step maintenance process beyond naming the steps (status → update → health → reboot → final) which is already in the schema. The contradiction with the schema's supported platforms also reduces completeness.

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?

Input schema coverage is 100%, and the description adds meaningful context beyond the schema: it explains each action's requirements and restrictions (e.g., 'Coolify servers only' for update/maintain) and clarifies the skipReboot parameter's use case. The server parameter description in the schema already mentions auto-selection, so the description reinforces without redundancy.

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 identifies the tool's purpose: maintaining Kastell servers with specific actions (update, restart, maintain). It distinguishes between server types (Coolify vs bare) and provides action details. However, there is a discrepancy between the description claiming 'Coolify servers only' for update/maintain and the input schema describing 'managed servers — Coolify or Dokploy', which may confuse the agent.

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 guidance on when to use each action, including server type restrictions ('Coolify servers only', 'both modes'). It notes alternatives (e.g., 'Snapshot not included — use server_backup tool') and limitations ('Manual servers: restart not available'), helping the agent choose correctly.

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