caddy_revert

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

Annotations already declare destructiveHint=true, and the description adds valuable context: snapshots are kept in-memory (last 10), apply requires confirm=true as a safety, and list/save are non-destructive actions. This goes beyond the annotations, though it doesn't detail the exact behavior of apply (e.g., whether it restarts the server).

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 concise and front-loaded: it opens with the tool's purpose, then explains the snapshot lifecycle and actions in a structured, easy-to-scan format. Every sentence adds necessary information without 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?

The tool has three distinct actions, and the description covers all of them with key details (timestamps, manual save, confirm requirement, retention limit). There is no output schema, but the description explains what each action produces. It could mention more about apply's effects, but the essentials are covered.

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 the schema already documents all three parameters. The description adds some context by linking actions to parameters (e.g., 'apply' needs confirm=true, index for 'apply'), but this is minimal beyond the schema's existing descriptions. Baseline 3 is appropriate.

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, with a specific verb ('Manage') and resource ('config snapshots'). It distinguishes from sibling tools like caddy_load by linking snapshots to auto-capture before caddy_load and enumerating specific actions (list, save, apply).

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 clear context: snapshots are auto-captured before caddy_load, implying use this tool to inspect or undo changes from caddy_load. It also explains the actions and the confirm requirement for apply. While it doesn't explicitly list alternatives or exclusions, the context is sufficient to guide when to use it.

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