undo_apply

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

With no annotations, the description must disclose behavioral traits. It tags the tool as [WRITE][risk=medium], explains the mutation behavior, the one-time-use constraint, and the dry_run preview. It does not cover error cases or side effects, but the core behaviors are transparent.

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 reasonably concise, using a structured format with tags and Args. The first line summarizes the core action. However, the docstring format adds some length; it could be slightly tighter without losing clarity.

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?

Given the simple parameter set (3 params, no nested objects) and no output schema, the description covers the key usage details: what the tool does, how to use dry_run, and the one-time constraint. It lacks explicit return value information, but the behavior is well-specified for its complexity.

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% (only titles), so the description must add meaning. It explains that 'undo_id' comes from undo_list or an '_undo_id' field, 'dry_run' previews the inverse call, and 'target' is passed through to the inverse tool. This adds significant context beyond the schema.

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 applies a recorded undo by dispatching its inverse tool. It distinguishes from sibling 'undo_list' by specifying that it executes the undo, not just lists it.

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 explains when to use dry_run for preview and notes that a token can only be applied once. It also mentions that the real risk is recorded in the inverse tool. However, it does not explicitly state when not to use this tool or provide alternatives beyond dry_run.

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