Rollback Change

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

Annotations already indicate destructiveness (destructiveHint=true). The description adds context on the rollback process (reads snapshot, computes diff, applies reverse diff) and the safety net of dryRun. It does not contradict annotations and provides meaningful behavioral detail beyond them.

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 three sentences: first states purpose, second explains mechanism, third gives dryRun guidance and config requirement. Each sentence is essential and front-loaded. No redundant text.

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 core behavior and dryRun, but omits critical details: it does not mention the confirmationToken parameter (required for actual destructive rollback) nor explain what the tool returns. With no output schema, these omissions hinder a complete understanding of tool usage.

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?

All parameters are described in the schema (100% coverage), so the description adds minimal new semantic value. It mentions dryRun's effect and the journal ID's role, but these are already clear from schema 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 restores RouterOS state before a write, using a journal ID. It explains the mechanism (reads snapshot, computes diff, applies reverse diff). This distinguishes it from siblings like apply_plan or plan_changes, as no other tool handles rollback.

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 implies usage for undoing a write and provides guidance on using dryRun for preview. However, it does not explicitly contrast with alternatives or provide when-not-to-use scenarios, such as when rollback is not feasible. The config requirement is mentioned but not as a usage guideline.

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