Remove a file or directory from the local filesystem. Set recursive true to delete directories; undo changes with checkpoint_rewind.
Delete a file, or a directory when recursive is true. Undoable with checkpoint_rewind.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Path | |
| recursive | No | ||
| allowPartialUndo | No | Proceed even if the change is too large to snapshot completely (undo would be partial) |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: deletions are recoverable via checkpoint_rewind, and the recursive flag governs whether directories are affected at all. It stops short of describing failure modes or snapshot limits.
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?
Two tight sentences with the primary action front-loaded and the recovery mechanism stated second. Nothing is wasted and no clause is self-evident 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 destructive mutation with no output schema, the description covers undo and recursive scope, which is the essentials. It omits edge cases an agent needs: behavior on non-empty directories, permission requirements, and whether path must exist or can be relative.
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 67% and the description adds real meaning for 'recursive' (controls directory deletion) and echoes partial-undo semantics for allowPartialUndo. But 'path' remains an uninformative 'Path' string in the schema with no format guidance (relative vs absolute), so the description does not fully compensate for the coverage gap.
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 and resource ('Delete a file') and explicitly handles the directory case via the recursive flag, so the scope is unambiguous. There is no sibling delete tool to differentiate from, so it earns a 4 rather than a 5.
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?
It gives the branch condition for recursive (directories) and points at checkpoint_rewind for recovery, which is useful implicit guidance. However, it never says when to prefer this tool over alternatives such as moving to trash, nor what happens when a non-empty directory is deleted without recursive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.