undo_apply

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

With no annotations provided, the description carries the full burden, and it does well. It discloses the write operation and risk level, explains the inverse tool runs with its own risk/audit, emphasizes that a token can only be applied once, and mentions the dry_run preview. This provides thorough behavioral context.

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 front-loaded with the action and risk, followed by concise explanatory notes and an Args list. Every sentence contributes value; no fluff or 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?

The description covers the key behavior, args, and constraints, making it effective for a 3-parameter tool with no output schema. Minor omissions include the return format or what happens after a successful apply, but overall it is complete enough for safe use.

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 the description must explain parameters, and it does. It explains undo_id, dry_run, and target in plain language, including sources and behavior. This adds significant meaning beyond the bare 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's purpose: 'Apply a recorded undo by dispatching its inverse tool.' It uses a specific verb ('apply') and resource ('recorded undo'), and it distinguishes itself from sibling tools like undo_list (which lists undos) by focusing on the application step.

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 context ('Apply a recorded undo') but does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or conditions. It mentions dry_run as a preview, but no explicit 'use this when...' guidance.

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