Skip to main content
Glama
runtimeguard

ai-runtime-guard

by runtimeguard

delete_file

Delete files with policy enforcement and optional backup, ensuring safe file removal within configured boundaries.

Instructions

Delete a single file after policy checks and optional pre-delete backup.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYes
ctxNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The core implementation of the delete_file tool. Validates path policy, checks file exists, refuses directories, performs optional backup, uses os.remove() to delete the file, and returns a result message.
    def delete_file(path: str, ctx: Context | None = None) -> str:
        """Delete a single file after policy checks and optional pre-delete backup."""
        context_tokens = activate_runtime_context(ctx)
        path = str(pathlib.Path(WORKSPACE_ROOT) / path) if not os.path.isabs(path) else path
    
        try:
            refresh_policy_if_changed()
            path_check = check_path_policy(path, tool="delete_file")
            if path_check:
                result = PolicyResult(allowed=False, reason=path_check[0], decision_tier="blocked", matched_rule=path_check[1])
            else:
                result = PolicyResult(allowed=True, reason="allowed", decision_tier="allowed", matched_rule=None)
    
            if result.allowed:
                if not os.path.exists(path):
                    append_log_entry(build_log_entry("delete_file", result, path=path, error="file not found"))
                    return f"Error: file not found: {path}"
    
                if os.path.isdir(path):
                    result = PolicyResult(
                        allowed=False,
                        reason=f"'{path}' is a directory  -  delete_file only removes individual files. Use execute_command for directory operations (note: bulk/recursive deletions are also subject to policy).",
                        decision_tier="blocked",
                        matched_rule=None,
                    )
    
            log_entry = build_log_entry("delete_file", result, path=path)
            if not result.allowed:
                append_log_entry(log_entry)
                return f"[POLICY BLOCK] {result.reason}"
    
            backup_enabled = bool(POLICY.get("audit", {}).get("backup_enabled", True))
            backup_location = backup_paths([path]) if backup_enabled else ""
            if backup_location:
                log_entry["backup_location"] = backup_location
    
            append_log_entry(log_entry)
    
            try:
                os.remove(path)
            except OSError as e:
                return f"Error deleting file: {e}"
    
            return f"Successfully deleted {path}. " + (
                f"Backup saved to {backup_location}  -  the file can be recovered from there."
                if backup_location
                else "No content-change backup was needed."
            )
        finally:
            reset_runtime_context(context_tokens)
  • src/server.py:21-31 (registration)
    The MCP server registers delete_file as a tool via mcp.tool()(delete_file) in a loop over the tool list.
    for tool in [
        server_info,
        restore_backup,
        execute_command,
        read_file,
        write_file,
        edit_file,
        delete_file,
        list_directory,
    ]:
        mcp.tool()(tool)
  • Re-exports delete_file from file_tools module in the package's __init__.py.
    from .file_tools import delete_file, edit_file, list_directory, read_file, write_file
    from .restore_tools import restore_backup
    
    __all__ = [
        "server_info",
        "execute_command",
        "read_file",
        "write_file",
        "edit_file",
        "delete_file",
        "list_directory",
        "restore_backup",
    ]
  • Lists delete_file as one of the AIRG MCP tools in the config manager.
    AIRG_MCP_TOOLS = [
        "server_info",
        "restore_backup",
        "execute_command",
        "read_file",
        "write_file",
        "edit_file",
        "delete_file",
        "list_directory",
    ]
  • Maps the 'Delete' action from codex/AirG to the MCP tool name 'mcp__ai-runtime-guard__delete_file'.
        "Delete": "mcp__ai-runtime-guard__delete_file",
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.5.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the burden. It mentions 'policy checks and optional pre-delete backup,' which adds behavioral context beyond a bare 'delete file.' However, it doesn't disclose failure modes, reversibility, or authentication needs.

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?

Single sentence, no fluff, front-loaded with action and context. Every word earns its place.

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

Completeness3/5

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

For a simple delete tool with output schema, description covers policy and backup but leaves parameter details unclear. Adequate but not comprehensive.

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

Parameters2/5

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

Schema coverage is 0%, so description must compensate. It does not explain what 'path' should be (e.g., absolute vs relative) or what 'ctx' is. It adds minimal value beyond parameter names.

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?

The description clearly states the action (delete), the resource (a single file), and adds specific context (policy checks and optional pre-delete backup). This distinguishes it from siblings like edit_file, read_file, etc.

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

Usage Guidelines2/5

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

No guidance on when to use this tool vs alternatives like restore_backup or edit_file. It does not mention prerequisites, limitations, or when not to use.

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