rollback_site

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

Beyond the destructiveHint annotation, the description discloses that the current config is backed up first (making the operation reversible), that confirm:true is required for action, that nginx -t is tested before keeping the result with the current config left in place on failure, and that nginx is not reloaded. This is exemplary behavioral disclosure for a state-changing tool.

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 but every clause earns its place: purpose, source of backups, default selection, reversibility, confirmation requirement, safety behavior, and the reload follow-up. The most important guidance is front-loaded, and the length is justified for a destructive operation.

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 mutation tool with destructiveHint, the description covers prerequisites (confirm), failure behavior (nginx -t leaves current config intact), reversibility (current config backed up first), data source (list_site_backups), and the required next step (reload_nginx). Together with the output schema and the input schema, an agent has everything needed to invoke it correctly and understand consequences.

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 domain, confirm's dry-run behavior, and backup_filename's default. The description adds workflow context around the parameters (where backups come from, the flip-back behavior, the reload caveat) but does not materially change or extend the parameter semantics beyond what the schema states.

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 opens with a specific verb and resource: 'Undo a config change' targeting the site's current nginx config. It also distinguishes the mechanism from related operations by identifying which tools produce the backups it reverts to, making it clear this is the revert-to-previous-change tool rather than a generic restore.

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?

It clearly states when to use the tool ('undo a config change'), explains the default behavior (newest backup = state before last change), and provides a critical follow-up instruction ('Does NOT reload nginx - call reload_nginx afterward'). It does not explicitly say 'use restore_site instead when you want a specific older backup,' but the backup_filename parameter and reference to list_site_backups imply that workflow.

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