Loading ToolBench
NestJS-based MCP server with SSE transport providing mathematical tools
Single tool 'sum' has a valid schema with typed parameters (a, b as numbers) but critical gaps in descriptions. Tool description is minimal (33 chars, below 50-char baseline for clarity). Parameter descriptions are completely absent, both 'a' and 'b' have null descriptions in the schema, violating the requirement that every parameter must have a description explaining what it controls. The tool name 'sum' lacks an action verb (should be 'calculate_sum' or 'add_numbers'). No output schema is documented. No error handling guidance. The tool is READ_ONLY and trivial, but the definition quality issues are structural and would cause LLM confusion in a production setting.
Returns the sum of two numbers
Missing parameter descriptions: both 'a' and 'b' parameters have null descriptions. LLMs cannot infer what these parameters control without explicit text.
Tool name lacks action verb. 'sum' is a noun; should be 'calculate_sum' or 'add_numbers' to signal the action to the LLM.
Tool description is too brief (33 characters). Baseline is 50-200 chars for clarity. Current description 'Returns the sum of two numbers' lacks context on when to use this tool or what it returns structurally.
No output schema documented. LLMs cannot plan downstream tool calls or extract fields without knowing the response structure.
No error handling guidance. If the tool fails (e.g., invalid input), there is no recovery hint for the LLM.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | 2026-07-28+ | v2 |