Loading ToolBench
MCP server for authoring, previewing, and verifying FactoryTalk Optix Studio changes via the emulator, single Windows box.
Single tool 'optix_status' with significant definition gaps. Tool name lacks action verb (should be 'get_optix_status' or 'check_optix_status'). Description is extremely long (600+ chars) and verbose, violating the 10-1024 char guideline. Input schema present with enum constraint (health|doctor|services|version), but parameter description is embedded in tool description rather than in schema. No output schema documented. No error handling guidance. Tool appears to consolidate four formerly separate tools but lacks clear composition documentation.
Deploy-stack status family — ONE tool, pick an `action`. Consolidates optix_health / optix_doctor / optix_services_status / optix_studio_version (each formerly its own tool); replaced cleanly, no deprecated aliases. These four are HETEROGENEOUS — pick the one that matches what you actually need, they are not interchangeable: action: - "health" — FAST preflight config snapshot (export-based, v0.2.x): projects_root, studio_exe, runtime_dir, interactive_session, bind config. Use this when the user asks "is everything wired up?", "is studio installed?", or before a deploy attempt to fail fast on missing config. - "doctor" — setup-FIX checklist: every prerequisite plus a plain-English fix for each. `ready` is True when the REQUIRED deps (Studio, projects folder) are present; feature checks (bridge, cdp, deploy creds, interactive session) report their own fix and gate only their own feature. Use this for first-time setup, after a reboot/config
Tool name 'optix_status' lacks action verb. Should be 'get_optix_status', 'check_optix_status', or 'describe_optix_status' to signal intent to LLM.
Tool description exceeds 1024 chars (approximately 600+ chars observed). Violates pattern guideline of 10-1024 chars. Description should be concise; action-specific details belong in parameter descriptions.
No output schema documented. LLM cannot predict what fields to expect from 'health', 'doctor', 'services', or 'version' actions. Each action returns heterogeneous data but no structured response definition provided.
Parameter 'action' description embedded in tool description rather than in schema. Schema should include per-enum-value descriptions explaining what each action does and when to use it.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 48 | 2026-07-28+ | v2 |
No error handling guidance. Tool description mentions 'ready' boolean and 'fix' checklist but does not document error responses, failure modes, or recovery steps for LLM.