undo_apply

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses that the inverse runs through its own governed tool, making the 'real risk tier recorded there,' and explains the dry_run preview and single-use token behavior. While it doesn't cover permissions or full consequences of applying, this is solid transparency for a mutating tool without annotation support.

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 well-structured and concise, starting with a clear summary sentence, then necessary behavioral notes, and a structured Args section. Every sentence contributes value: the risk-tier note, dry_run preview, single-use constraint, and parameter explanations are all essential. It is front-loaded with the summary and avoids 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?

Given there is no output schema, the description need not explain return values. It covers the tool's purpose, usage context, parameter semantics, and key behavioral traits (preview, single-use). The only minor gap is lack of what to expect after a successful apply (e.g., confirmation), but this is not critical for a simple tool with three parameters.

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 description coverage is 0%, and the description compensates excellently by explaining each parameter. undo_id is defined as coming from undo_list or _undo_id in write results, dry_run is described as previewing the inverse call, and target is explained as being passed through to the inverse tool. This adds significant meaning beyond the bare schema fields.

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: 'Apply a recorded undo by dispatching its inverse tool.' This is a specific verb+resource combination that distinguishes it from sibling undo_list, which lists undos. The reference to undo_id from undo_list further differentiates the apply action from listing.

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 clear context: you apply a recorded undo, can preview with dry_run=True, and a token can only be applied once. It explains where to obtain undo_id, but does not explicitly state when not to use the tool or name alternatives beyond the implicit undo_list. This is clear context without explicit exclusions, earning a 4.

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