Loading ToolBench
Single tool with minimal documentation. The 'add' tool has a functional schema but critically lacks parameter descriptions and has a terse tool description (12 characters). Per the rubric baselines, average tool description length is 194 chars (p10=34) and 100% of A+ tools have parameter descriptions for every input. This server meets neither standard. Parameter 'a' and 'b' have no descriptions, violating the pattern:tool-description requirement. The tool is readable and has proper type definitions, but insufficient context for LLM decision-making.
Add two numbers
Tool description is 12 characters ('Add two numbers'), below the 34-char p10 baseline for A+ tools. LLM cannot infer when to use 'add' vs. other numeric tools or whether this performs any side effects.
Parameter 'a' has no description. Parameter 'b' has no description. Rubric requires every parameter to have a non-empty description explaining what it controls. LLMs cannot infer that 'a' and 'b' are summands vs. dividend/divisor.
No input validation guidance or constraints documented. No mention of bounds (e.g., max safe integer, overflow behavior). LLMs may pass extreme values that cause unexpected behavior.
Output schema not documented. Rubric requires documentation of what the tool returns so LLMs can plan downstream steps. 'add' returns an int, but no schema annotation exists in code or docs.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 41 | 2026-07-28+ | v2 |
| 2026-03-09 | F | 29 | - | v1 |
No error handling documentation. What happens if inputs overflow? What if types are invalid? No recovery guidance for LLM.