Loading ToolBench
A compiled MCP (Model Context Protocol) server that exposes the SwiftUI Pro agent skill content over stdio JSON-RPC 2.0.
Three tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. Tool names follow verb_noun convention (list_, get_), which is good. However, descriptions are minimal (10-50 chars), parameter descriptions are absent or trivial, and output schemas are not documented. No error handling guidance. The 'topic' parameter in get_swiftui_reference has an enum constraint in the description but lacks formal schema enum declaration. No tool annotations (readOnlyHint, etc.). Overall structure is present but falls short of production quality.
Get the SwiftUI Pro reference guide for a specific topic.
Get the full SwiftUI Pro skill definition including review process and output format.
List all available SwiftUI Pro reference topics.
Parameter descriptions missing or trivial. The 'topic' parameter in get_swiftui_reference has only a bare enum list in the description; no explanation of what 'topic' controls or when to use each value.
Output schemas not documented. Tools return text content but no schema is provided describing the structure, fields, or format of the returned data. LLMs cannot plan downstream calls without knowing what fields to expect.
Tool descriptions are too brief (10-50 chars). Descriptions lack context on WHEN to use each tool, WHAT it returns, and any prerequisites. Baseline for A+ tools is 50-200 chars with clear intent.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 42 | 2026-07-28+ | v2 |
No error handling guidance. If an invalid topic is passed to get_swiftui_reference, the tool returns null but provides no recovery hint (e.g., 'Call list_swiftui_topics first to see valid options').
No tool annotations. Tools lack readOnlyHint, destructiveHint, or idempotentHint metadata. All three are read-only and idempotent, but this is not declared in the schema.