Loading ToolBench
MCP server providing design pattern templates for AI coding agents
Neither tool documents output structure for LLM consumption. No error handling guidance provided. Naming follows verb_noun convention well. Descriptions are within baseline range (194 char average) but lack WHEN/WHY context and recovery guidance.
Get structural constraints and anti-patterns for a specific design pattern in a specific language. Returns compact plain text (~300-500 tokens) optimized for LLM consumption. Call this when you know which pattern to implement.
Map a problem description to design pattern name(s). Returns up to 3 ranked suggestions with confidence scores. Call this when you know the problem but not which pattern to apply.
Output schemas not documented. LLMs cannot plan downstream calls or extract fields without knowing response structure. suggest_pattern returns JSON but structure undefined; get_template returns formatted text but field mapping unclear.
Parameter descriptions lack format/constraint details. language parameter in get_template lists valid values in schema enum but NOT in description text. LLMs cannot read JSON Schema, they rely on description text.
No error handling guidance. If pattern not found or language unsupported, LLM receives error but no recovery path.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 57 | 2026-07-28+ | v2 |
Descriptions lack WHEN/WHY context. suggest_pattern says 'Call this when you know the problem but not which pattern to apply' (good), but get_template description does not explain when to call it vs suggest_pattern or how they compose. State WHAT the tool does, WHEN to use it, and any prerequisites.'
category parameter in suggest_pattern lacks description text explaining what each enum value means. 'modern' and 'architectural' are vague, does 'modern' mean recent patterns? Does 'architectural' mean system-level? LLM cannot infer.