server_maintain

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

The description adds significant behavioral context beyond annotations: requires SSH access for update, API tokens for restart/status, and blocks certain actions on bare/manual servers. Annotations already provide idempotentHint=true, but the description details preconditions and restrictions. A minor gap: potential downtime effects are not mentioned, but overall strong transparency.

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 dense and informative, packing a lot of info into a single paragraph. It is front-loaded with the verb ('Maintain') and actions. While it could be more structured (e.g., bullet points), every sentence adds value and there is no fluff. Slightly above average for conciseness.

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 all necessary context: actions, server type restrictions, auth requirements (SSH, API tokens), alternative for snapshots (sibling tool), and even business-hour hint. With output schema existing, return values are handled externally. This is a complete, self-contained description for a moderately complex tool.

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?

With 100% schema description coverage, baseline is 3. The description adds value by explaining business hour usage for skipReboot and clarifying action applicability (e.g., maintain includes reboot steps). However, it largely reiterates the schema descriptions; no new parameter semantics beyond that. A solid 4 for complementing the schema 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 states the tool performs server maintenance on Kastell servers, listing three distinct actions ('update', 'restart', 'maintain') with explicit verb+resource. It differentiates between Coolify and bare servers, and mentions that snapshot is handled by a sibling tool. This makes the purpose unambiguous and distinct from siblings.

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 when-to-use guidance for each action, including server type restrictions (Coolify-only for update/maintain, both for restart) and business-hour usage of skipReboot. It also tells when NOT to use this tool (for snapshots, use server_backup) and notes manual server limitations. This is comprehensive alternative referencing.

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