undo

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the target (`project.json`) and the mechanism (restoring a snapshot from before the specified edit batches), but does not cover permissions, reversibility of the undo, error behavior, or return values.

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 a single efficient sentence, with the primary action front-loaded and no unnecessary filler.

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 simple undo tool with two parameters, the description explains the core state change well enough to understand the operation. However, with no annotations, no output schema, and 0% parameter description coverage, it leaves gaps around the `project` parameter and return behavior.

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%, so the description must compensate. It clarifies that `steps` refers to edit batches, which adds meaning beyond the schema's integer type, but the required `project` parameter is not described or contextualized.

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 names a specific verb (`Undo`) and resource (`edit batches`), and specifies the effect on `project.json`. It clearly differentiates an undo operation from sibling tools such as `edit`, though it does not explicitly name an alternative tool.

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?

Usage is implied by the name and description: use this tool to revert prior edit batches. However, there is no explicit guidance on when not to use it, prerequisites, or alternatives to consider.

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