ProjectOpenHandMonk

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

34/34 tools missing one or more hints — server_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); fetch_data (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_records (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +31 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — execute_python_code deletes at line 64 (os.unlink(temp_path))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — dns_lookup (line 178: result = subprocess.run()

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

33/34 tool handlers declare input schemas (97%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

19/34 tool handlers wrap calls in try/catch (56%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

6 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.