Remove files from the working tree and index in a local Git repository, optionally only from the index.
Remove files from the working tree and index.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Optional local working directory or repository path. | |
| paths | Yes | Paths to remove. | |
| cached | No | Only remove from the index. |
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 full behavioral burden. It states the removal scope but omits critical behaviors for a destructive tool: permanence/reversibility, whether it requires a clean working tree, whether the removal can be recovered, and how the 'cached' flag alters behavior. This is a significant gap for a git rm operation.
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 front-loaded sentence with no wasted words. It is appropriately sized for a simple statement of purpose, though it is arguably too terse for a destructive tool, which borders on under-specification rather than verbosity.
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 mutation tool with no annotations and no output schema, the description should disclose safety and operational context (destructiveness, recovery, prerequisites). It provides only the basic action, leaving an agent without enough information to use git_rm safely or correctly in ambiguous situations.
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%, with clear descriptions for cwd, paths, and cached. The description adds no parameter meaning beyond the schema, which is the expected baseline when the schema already documents all parameters.
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 gives a specific verb ('Remove') and resource ('files from the working tree and index'), making the core action clear. However, it does not differentiate from sibling tools like git_clean, git_restore, or git_reset, nor does it specify that it targets tracked files, so an agent cannot easily distinguish it from alternatives.
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 guidance on when to use this tool versus alternatives such as git_clean or git_restore, nor any prerequisite information (e.g., clean working tree). The description is purely declarative and leaves selection entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.