undo_list

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

With no annotations provided, the description carries the full burden and does so excellently. It discloses that truncated is measured by fetching an extra row, not guessed, and that effectVerified=false means the inverse operation is only probable and should be checked against live state. This is substantive behavior beyond basic operation.

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 a clear first sentence stating purpose, then flows into return format details and parameter docs. Every sentence earns its place; it is slightly long but dense with necessary information and well-organized.

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?

Even though there is no output schema, the description explains the exact return shape and the meaning of the key fields (truncated, effectVerified). It covers parameter behavior and provides enough detail to use the tool correctly and interpret results confidently.

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 schema has zero coverage, so the description fully compensates by explaining both parameters: limit has a default, a cap, and controls returned rows; target is explicitly noted as unused but accepted for CLI uniformity. This removes any ambiguity.

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 states a specific verb ('List') and resource ('recorded, not-yet-applied undo tokens'), and clarifies the most-recent-first ordering. It also distinguishes itself from the sibling tool 'undo_apply' by explaining that the returned undoId is intended for that tool, making its role as a listing counterpart clear.

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 gives clear context: it is for listing undo tokens before applying them, and explicitly instructs using the undoId with undo_apply. It also advises re-running with a higher limit when truncated is true. It does not explicitly name an alternative for exclusion, but the usage guidance is otherwise strong.

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