Undo

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

With no annotations, the description carries the full burden, and it does disclose valuable behavior: the granularity is exactly one edit, and the affected artifact is either the in-view zone file or an unsaved data file by extension. It omits what happens when the undo stack is empty, whether the file must be open/unsaved, and whether the undo is itself reversible via redo.

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?

A single front-loaded sentence that leads with the action and its granularity, then the two target modes. The nested parenthetical of file extensions is dense and slightly awkward, but no sentence is wasted.

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?

For a one-optional-param tool with no annotations and no output schema, the essential invocation semantics are present. What is missing is failure behavior (nothing to undo, stale path) and any hint of the return value, which matter for an agent driving an editing loop.

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% for the single optional 'file' parameter, so the description must compensate — and it does, defining the value as a path drawn from get_state's list of unsaved files and enumerating the relevant extensions (.gca, carstatus.car, .ops, .efl). The remaining gap is path format (absolute vs. relative) and the default when the parameter is omitted.

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?

States a specific verb (undoes) and a specific resource scope (one position edit), and distinguishes the two targets: the zone file currently shown versus a named data file. It does not, however, differentiate itself from the sibling redo or from revert_file/reset_items, so the boundary is only partially drawn.

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 when each mode applies (edited the zone in view vs. edited an unsaved data file), which is useful implicit routing. But it never names alternatives such as redo, revert_file, revert_image, or reset_items, and it gives no condition for choosing between undo and those recovery tools.

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