Loading ToolBench
Calculator demo with SSE transport for Model Context Protocol
Both tools have critical definition gaps. Parameter descriptions are also null for all inputs. While schemas are present with proper types (number), the lack of any descriptive text makes these tools unusable by LLMs. Tool names are reasonable (verb_noun pattern) but cannot compensate for missing documentation. No error handling, output schemas, or composition guidance.
All tool descriptions are missing or empty. LLMs cannot determine when or why to select these tools without descriptions.
All parameter descriptions are null. Parameters 'weightKg', 'heightM', 'a', 'b' lack any documentation of their meaning, format, or constraints.
No output schema documentation. Callers cannot predict the structure of responses or plan downstream tool calls.
No error handling or recovery guidance. If a tool fails, the LLM has no actionable next step.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | 2026-07-28+ | v2 |
Parameter constraints missing. 'heightM' should document valid range (e.g., 0.5 - 2.5 meters); 'weightKg' should specify minimum (e.g., 1 - 500 kg). Unbounded numbers invite invalid LLM inputs.