caddy_revert

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

Annotations declare destructiveHint=true, and the description aligns by noting 'apply' restores a snapshot and requires confirm=true. It adds valuable context beyond annotations: snapshots are auto-captured before caddy_load, are kept to the last 10, and are lost on server restarts unless a directory is configured. This discloses persistence and destructive implications that annotations alone do not convey. No contradiction exists.

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 two sentences, front-loaded with the core purpose, and each clause earns its place. It packs a lot of information—auto-capture, retention, persistence caveat, and actions—without bloat. The structure is efficient and easy to parse.

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 tool with three parameters and no output schema, the description covers the essential behavior: what actions exist, persistence, and the safety requirement for apply. It doesn't describe return types (not required without output schema) or error handling, but those are minor. It could go further by explicitly stating that 'apply' overwrites the active config, but that is strongly implied by 'restores a snapshot'. Overall it is sufficiently complete for an agent to call it correctly.

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 description coverage is 100%, so each parameter is documented in the schema. The description nevertheless adds semantic value by explaining the meaning of each action value ('list' shows snapshots, 'save' captures, 'apply' restores), and reinforcing that confirm must be true for apply. While the schema already describes index as '0 = most recent', the description's action semantics help the agent understand the workflow without opening an enum.

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 manages config snapshots for rollback, and enumerates three specific actions (list, save, apply). This distinguishes it from sibling tools like caddy_load or caddy_config_set, which deal with live config rather than snapshots. The verb 'manage' plus the resource 'config snapshots' is specific and 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 explains when to use the tool (for snapshot operations) and includes a critical caveat about snapshots being memory-only and lost on restart unless CADDY_MCP_SNAPSHOT_DIR is set. It also notes that 'apply' requires confirm=true, which is a usage requirement. However, it does not explicitly contrast with alternatives like caddy_load or caddy_config_set, leaving some routing to inference. The context is clear but not fully explicit.

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