undo

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the mutation risk is known. The description adds the genuinely new fact that the revert is irreversible ('Cannot be redone'), which the annotations do not convey and which directly affects how cautiously an agent should invoke it. It stops short of explaining scope limits such as whether undo survives a new session.

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 tight sentence with the action first and the irreversibility warning last, where it lands hardest. Every clause earns its place and nothing is padded.

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 two-parameter tool with full schema coverage and annotations, the description covers what is reverted, on what, and that it is permanent. With no output schema it should ideally say what a successful undo returns or how failure is reported, but the core information an agent needs is present.

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 100% and both parameters (steps, project) carry their own descriptions, so the schema does the heavy lifting. The description's 'last edits' weakly implies the default single-step behavior but adds no format or boundary detail beyond the schema's minimum/maximum.

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 (revert) and resource (the last edits of a project), and the parenthetical '(any tool that changed it)' defines the scope of what can be undone. It is unambiguous, though it doesn't need sibling differentiation since no other tool in the list performs undo.

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 phrase 'any tool that changed it' implies this is the recovery path after a mutating tool ran, but there is no explicit when-to-use/when-not-to-use guidance, no mention of prerequisites, and no statement about how it interacts with the stack of prior edits beyond the implicit context.

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