Loading ToolBench
An MCP server deployed on Cloudflare Workers with OAuth 2.0 authentication and a demo tool for arithmetic operations
Single tool 'add' has a clear verb-noun name and basic schema with typed parameters. However, the description is extremely minimal (23 chars), barely meeting the 10-char floor but well below the 50-200 char LLM-optimized baseline. Parameter descriptions are present but terse (12-18 chars each). No output schema is documented. No error handling guidance. The tool is trivial (arithmetic), so composition and chaining concerns are muted, but the definition quality falls short of production standards.
Adds two numbers together
Tool description is too brief (23 chars). LLM-optimized descriptions should be 50 - 200 chars, explaining WHAT the tool does, WHEN to use it, and what it returns.
Parameter descriptions are minimal (12 - 18 chars). Should explain the expected format, range, and role. E.g., 'First number to add (integer or float)' instead of 'First number to add'.
Output schema is not documented. LLMs need to know what fields to expect in the response to plan downstream calls and extract data correctly.
No error handling guidance. If inputs are invalid (e.g., non-numeric), the tool should return a clear, actionable error message telling the LLM what to do next.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 56 | 2026-07-28+ | v2 |
No input validation or constraints. Numeric parameters should specify min/max bounds or precision to prevent absurd values (e.g., Infinity, NaN).