Loading ToolBench

Reading the current corpus…

genpark-autonomous-test-mutation-coverage-scorer-skill MCP server · F · ToolBench

← Browse

genpark-autonomous-test-mutation-coverage-scorer-skill

github.com/alphaparkinc/genpark-autonomous-test-mutation-coverage-scorer-skill

MCP Server for mutation testing coverage analysis and test suite quality evaluation using AST mutant generation

2026-07-28+STDIO1 tools

40/100

Definition Quality43

Protocol Readiness50

Supportability28

Spec posture

Inferred effective spec 2026-07-28+·current baseline 2026-07-28

Static source inference · medium confidence

Current-spec patterns detected

Summary

Single tool with basic schema and minimal description. Tool name lacks action verb (should be 'score_mutation' or 'evaluate_mutations'). Description is 73 chars, acceptable but generic. No output schema documented. No error handling guidance. No parameter constraints (enums, ranges, formats). Tool does not follow verb_noun naming convention.

Tools (1)

evaluate_mutation_scoreread onlysource verified43/100

Execute mutation testing on Python source code and test suite.

Issues (5)

CRITICALtool-description ↗

Missing parameter descriptions. 'original_code' and 'test_cases' have no descriptions in the schema, LLMs cannot infer what format test_cases should take (fn_name, args, expected structure is only in the description text, not in the schema).

evaluate_mutation_score

CRITICALtool ↗

No output schema documented. Tool returns JSON with 'msi', 'total_mutants', 'killed_mutants', 'survived_mutants', 'details' fields, but LLMs have no formal schema to understand the structure.

evaluate_mutation_score

HIGHtool ↗

Tool name does not start with action verb. 'evaluate_mutation_score' is awkward; 'score_mutations' or 'evaluate_test_coverage' would be clearer.

evaluate_mutation_score

HIGHrecovery-guide ↗

No error handling guidance. Code returns generic error messages ('Original code fails to execute', 'Baseline test case failed') without actionable recovery steps.

Recommendations

Add descriptions to all input parameters in the schema. For 'test_cases', specify: 'Array of test case objects, each with fn_name (string), args (array), and expected (any). Example: [{"fn_name": "add", "args": [2, 3], "expected": 5}]'.
Document the output schema explicitly. Define fields: msi (number 0-100), total_mutants (integer), killed_mutants (integer), survived_mutants (integer), details (array of {id, type, line, original, code}).
Rename tool to 'score_mutations' or 'evaluate_test_mutations' to follow verb_noun convention and improve LLM discoverability.
Add error handling guidance. Return structured errors like: {"status": "error", "message": "Original code syntax error at line 5", "recovery": "Fix the syntax error and retry"}.
Add parameter constraints: test_cases minItems=1, maxItems=100; original_code minLength=1, maxLength=50000. Prevents absurd inputs.

Score history

Overall score trend

First recorded score · v2 rubric

40/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	40	2026-07-28+	v2