Read a git diff from a local repository to inspect unstaged or staged changes. Specify an optional ref, range, or pathspec to view exactly the modifications you need.
Read a git diff from the local repository.
| Name | Required | Description | Default |
|---|---|---|---|
| cwd | No | Optional local working directory or repository path. | |
| ref | No | Optional ref, range, or pathspec to diff. | |
| staged | No | Use git diff --staged. |
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. 'Read' implies read-only, but it never states what is diffed by default (unstaged working-tree changes), whether output is truncated for large diffs, or how the result is formatted. For a no-annotation tool this is a significant gap.
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 with no filler. It is efficient, though the brevity borders on under-specification rather than genuine tightness.
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?
With no output schema, no annotations, and three all-optional parameters, the description should clarify the default diff target and return format. It leaves the agent to guess what a zero-argument call produces and how the diff is returned.
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 cwd, ref, and staged each documented in the schema, so the baseline of 3 applies. The description adds nothing beyond the schema, not even the default unstaged behavior implied by staged defaulting to false.
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 ('Read') and resource ('git diff') scoped to 'the local repository'. It is unambiguous about the operation, but offers no differentiation from adjacent siblings like git_show or git_status, which could also surface change content to an agent unfamiliar with Git.
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 exclusions, and no mention of alternatives such as git_show (a specific commit's diff) or git_status (working-tree summary). The agent must infer usage purely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.