nitrostack

Tool annotations

76/676 tools have annotations

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

All four hints declared on every tool

631/676 tools missing one or more hints — scan_cloud_inventory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); audit_security_risks (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); calculate_idle_waste (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +628 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 — generate_network deletes at line 177 (os.remove(f))

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 — run_gui_simulation (line 370: subprocess.Popen(cmd))

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

Tool test coverage

Only 71/676 tools referenced in tests (11%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

2 calls in production code run through a shell (typescript/packages/core/src/ui-next/index.ts:107, typescript/packages/core/src/ui-next/index.ts:209)

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

Tool description accuracy

run_gui_simulation: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.