undo_list

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

Beyond the readOnlyHint annotation it discloses non-obvious behaviors: the one-extra-row truncation measurement, the meaning of effectVerified=false (probable vs confirmed changes), and that target is accepted only for CLI uniformity. These are exactly the kind of traits an agent cannot infer from the schema.

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?

Front-loaded with purpose, then return shape, then the critical effectVerified caveat, then args. Well organized, though the effectVerified paragraph is somewhat long and slightly repetitive in emphasizing the probable-not-confirmed distinction.

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?

With no output schema present, the description supplies the return shape ({undos, returned, limit, truncated}), the row semantics, and the safety caveat for applying entries. Nothing essential for correct invocation is missing.

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%, yet the args section documents limit (default 50, max 500) and explicitly marks target as unused. The description fully compensates for the undocumented 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?

Starts with a specific verb and resource: 'List recorded, not-yet-applied undo tokens (most recent first)'. It clearly distinguishes itself from the sibling undo_apply by framing the tokens as the input to that tool rather than the action itself.

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?

Explicitly tells the agent the follow-up workflow: 'Use the undoId with undo_apply', and the effectVerified note prescribes checking live state before applying. It lacks an explicit 'when not to use' but the context for invocation is clear.

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