undo_apply

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

With no annotations, the description carries full burden. It discloses dispatching the inverse tool, the governed execution, dry-run preview, and one-time token use. Lacks explicit mention of side effects like token consumption or error handling, but covers key behaviors.

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?

Five sentences with clear structure: purpose statement, behavioral details, parameter list. Front-loaded with '[WRITE][risk=medium]'. Every sentence adds value 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?

Describes parameters and overall mechanism, but lacks output description or error conditions. With no output schema, the agent is left guessing the return value. Adequate for a simple tool but not fully complete.

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 coverage is 0%, so description must compensate. It explains each parameter: undo_id source, dry_run purpose, and target pass-through. Adds meaningful context beyond schema types and defaults.

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 it applies a recorded undo by dispatching its inverse tool. It references undo_list as the source of undo IDs, distinguishing it from listing tools and other mutation tools like retry_pipeline or cancel_pipeline.

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?

Provides context for use: apply undo from undo_list, preview with dry_run, and notes that each token can only be applied once. Does not explicitly list when not to use or alternatives, but the implicit guidance is sufficient.

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