rollback_feature

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently lists the core actions (abort worktree, clean up branch, record reason), which conveys destructiveness and logging. However, it does not explicitly state that the branch is deleted by default (though implicit in 'cleans up branch') or mention irreversibility. It's adequate but not exhaustive.

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?

Two sentences, front-loaded with the primary action, followed by usage guidance. Every word earns its place — no redundancy or filler. The format is efficient and easy to scan.

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 moderate complexity (3 params, 1 required) and no output schema or annotations, the description covers purpose, actions, and usage context. It doesn't explain the default deletion of the branch or the post-rollback state, but these are partly covered by the schema. Overall, it provides enough context for an agent to decide when and how to invoke it.

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?

The input schema has 100% description coverage for all three parameters, so the baseline is 3. The description adds minimal parameter-specific meaning: 'records reason' alludes to the required 'reason' parameter, but doesn't explain 'keep_branch' or 'worktree_path' beyond what the schema already says. Since the schema already documents them, no significant extra value is added.

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's function: 'Rolls back a failed or unwanted feature' and specifies concrete actions: 'aborts worktree, cleans up branch, records reason.' This distinguishes it from sibling tools like abort_worktree, which likely only aborts the worktree, while rollback_feature handles the full cleanup. The verb 'rolls back' and resource 'feature' are 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 provides explicit when-to-use guidance: 'Use this when you need to abandon a feature without merging.' This tells the agent the appropriate context and implies it's not for completing or continuing a feature. It doesn't explicitly name alternatives or exclusions, but the 'use when' directive is clear enough.

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