Skip to main content
Glama
L-Jovi

Keyhole – Local files for ChatGPT

delete_file

DestructiveIdempotent

Delete a regular file (up to 8 MiB) from a writable workspace after verifying its SHA-256 hash, storing bytes for recovery via restore_change.

Instructions

Recoverably delete one regular file <=8 MiB from an rw space after checking its SHA-256. Stores original bytes in private local recovery history; use restore_change to undo. No directory or permanent deletion tool.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYes
workspaceYes
request_idYes
expected_sha256Yes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.2-demo.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already signal destructive=true and readOnly=false, but the description adds essential behavioral context: recovery semantics, storage of original bytes in private local recovery history, size limit, SHA-256 verification, and undo route. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences with no filler. Every clause earns its place: operation, constraints, recovery behavior, undo path, and exclusions are all covered efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive but recoverable tool, the description covers prerequisites, recovery, undo, and scope well. The main gaps are the role of request_id and the post-delete return value, especially with no output schema, but these are minor relative to the rich behavioral guidance provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It adds meaning to workspace (rw space), path (regular file ≤8 MiB), and expected_sha256 (checked before deletion), but request_id remains unexplained. This is partial compensation, not full.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Recoverably delete one regular file'), with clear constraints (≤8 MiB, rw space, SHA-256 check). Explicitly distinguishes itself from restore_change and from directory/permanent deletion tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear usage context: when to use it (deleting a regular file from an rw space), how to undo it ('use restore_change to undo'), and what it is not for ('No directory or permanent deletion tool'). This gives explicit routing guidance.

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