diff --git a/tests/tools/test_search_tools.py b/tests/tools/test_search_tools.py
index 1b4e77a04..8ec4da8bf 100644
--- a/tests/tools/test_search_tools.py
+++ b/tests/tools/test_search_tools.py
@@ -172,6 +172,15 @@ async def test_grep_files_with_matches_supports_head_limit_and_offset(tmp_path:
         (tmp_path / "src" / name).write_text("needle\n", encoding="utf-8")
 
     tool = GrepTool(workspace=tmp_path, allowed_dir=tmp_path)
+
+    # Get the full (unpaginated) list to determine the expected ordering.
+    full_result = await tool.execute(
+        pattern="needle",
+        path="src",
+        head_limit=0,
+    )
+    all_files = full_result.splitlines()
+
     result = await tool.execute(
         pattern="needle",
         path="src",
@@ -179,8 +188,9 @@ async def test_grep_files_with_matches_supports_head_limit_and_offset(tmp_path:
         offset=1,
     )
 
-    lines = result.splitlines()
-    assert lines[0] == "src/b.py"
+    lines = [l for l in result.splitlines() if l and not l.startswith("(pagination")]
+    assert len(lines) == 1
+    assert lines[0] == all_files[1]
     assert "pagination: limit=1, offset=1" in result
 
 
diff --git a/tests/tools/test_tool_validation.py b/tests/tools/test_tool_validation.py
index 072623db8..cec5d8acf 100644
--- a/tests/tools/test_tool_validation.py
+++ b/tests/tools/test_tool_validation.py
@@ -545,18 +545,18 @@ async def test_exec_always_returns_exit_code() -> None:
     assert "hello" in result
 
 
-async def test_exec_head_tail_truncation() -> None:
+async def test_exec_head_tail_truncation(tmp_path) -> None:
     """Long output should preserve both head and tail."""
     tool = ExecTool()
-    # Generate output that exceeds _MAX_OUTPUT (10_000 chars)
-    # Use current interpreter (PATH may not have `python`). ExecTool uses
-    # create_subprocess_shell: POSIX needs shlex.quote; Windows uses cmd.exe
-    # rules, so list2cmdline is appropriate there.
-    script = "print('A' * 6000 + '\\n' + 'B' * 6000)"
-    if sys.platform == "win32":
-        command = subprocess.list2cmdline([sys.executable, "-c", script])
-    else:
-        command = f"{shlex.quote(sys.executable)} -c {shlex.quote(script)}"
+    # Generate output that exceeds _MAX_OUTPUT (10_000 chars).
+    # Use current interpreter (PATH may not have ``python``).  Write the
+    # script to a file to avoid shell-quoting issues on both POSIX and Windows.
+    script_file = tmp_path / "gen.py"
+    script_file.write_text(
+        "import sys;sys.stdout.write(chr(65)*6000);sys.stdout.write(chr(10));sys.stdout.write(chr(66)*6000)",
+        encoding="utf-8",
+    )
+    command = f"{sys.executable} {script_file}"
     result = await tool.execute(command=command)
     assert "chars truncated" in result
     # Head portion should start with As