Jarvis

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

15/15 tools missing one or more hints — call_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); web_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze_document (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +12 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 — run_tests deletes at line 128 (shutil.rmtree(temp_dir))

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.

Tool inputs are validated

4/7 tool handlers declare input schemas (57%)

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

Tool handlers catch errors

Only 1/7 tool handlers wrap calls in try/catch (14%)

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

7 child_process calls — runs shell commands

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