Undo specified Git commits by creating inverse commits in a local repository. Use noCommit to apply changes without committing, or set cwd to target another repo.
Revert existing commits.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Optional local working directory or repository path. | |
| revs | Yes | Commit revisions to revert. | |
| noCommit | No | Apply revert without committing. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden, yet it only restates the operation. It does not disclose that revert produces new inverse commits rather than rewriting history, that conflicts are possible, or that an existing commit is required, all of which materially affect how an agent invokes it.
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?
It is a single front-loaded sentence with zero waste, which is structurally sound. The terseness tips into under-specification for a history-mutating git command, so it is efficient but not adequately sized to its complexity.
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 mutating, conflict-prone git command with no annotations and no output schema, the description omits required preconditions, conflict behavior, and the side effect of creating new commits. An agent could select it correctly by name but would lack the context to invoke it safely.
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 100%, and the schema itself documents revs, noCommit (apply without committing), and cwd, so the description correctly adds nothing new. Baseline 3 applies since the schema does the semantic work.
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?
"Revert existing commits" gives a specific verb and resource, so the basic operation is legible. However, it does nothing to separate this from closely related siblings like git_reset, git_restore, or git_cherry_pick, leaving the agent to infer the distinction from git knowledge alone.
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?
There is no when-to-use guidance, no mention of prerequisites (e.g. a clean working tree), and no routing to alternatives such as git_reset for history rewriting. With 25 sibling git tools, the absence of any disambiguation is a real gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.