Loading ToolBench
An MCP server providing mathematical calculation tools and utilities for arithmetic operations, trigonometry, and data transformations
This calculator server has 21 tools with consistent but minimal quality. All tools have descriptions (10-50 chars, mostly under 20), which violates the 20-char floor for scoring. Input schemas are present and properly typed, but descriptions lack context on WHEN to use tools or what they return. No error handling guidance, no output schemas documented, and several tools have vague or incomplete descriptions ('special mining tool', 'log of a number'). Tool naming is verb-based but generic (add, subtract, multiply). The server mixes unrelated concerns: basic math (add, subtract), trigonometry (sin, cos, tan), image processing (create_thumbnail), string manipulation (strings_to_chars_to_int), and GUI automation (open_powerpoint_and_add_text_gui). No tool annotations, no pagination, no recovery guidance. Baseline: 194 chars avg description; this server averages ~25 chars.
Add two numbers
Add all numbers in a list
Cube root of a number
cos of a number
Create a thumbnail from an image
Divide two numbers
factorial of a number
Return the first n Fibonacci Numbers
Descriptions are critically short (10-50 chars, mostly <20). Rubric floor is 20 chars minimum; most descriptions fail this. Examples: 'log of a number' (15 chars), 'sin of a number' (15 chars), 'special mining tool' (18 chars). LLMs cannot determine WHEN to use these tools or what they return.
No output schemas documented. Tools return scalars (int, float, bool, list) but LLMs have no formal specification of return types or structure. Baseline: 100% of A+ tools document return types.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 49 | 2026-07-28+ | v2 |
Return sum of exponentials of numbers in a list
Check if a number is prime
log of a number
special mining tool
Multiply two numbers
Open PowerPoint GUI first and then add Title and text to a new slide using AppleScript
Power of two numbers
remainder of two numbers divison
sin of a number
Square root of a number
Return the ASCII values of the characters in a word
Subtract two numbers
tan of a number
Tool 'mine' has vague name and description. 'mine' does not convey action (verb_noun pattern). Description 'special mining tool' is non-descriptive. What does it compute? When should an LLM call it instead of subtract?
No error handling or recovery guidance. Tools like divide() and log() can fail (division by zero, log of negative). No error messages guide LLMs on what to do next. Baseline: error responses must tell LLM what to do next.
Tool composition violates single-responsibility principle. Server mixes math (add, subtract), trigonometry (sin, cos, tan), image processing (create_thumbnail), string manipulation (strings_to_chars_to_int), and GUI automation (open_powerpoint_and_add_text_gui). These are unrelated domains; splitting into separate servers would improve clarity and reusability.