score_response_quality
Evaluate response quality across substance, specificity, hedge avoidance, and structure. Discover the weakest dimension and receive targeted advice to improve it.
Instructions
Score a response across four quality dimensions: substance, specificity, hedge avoidance, and structure.
REQUIRED INPUT FORMAT — copy this structure exactly: {"response_text":"The full text of the response you want to evaluate for quality. It should be at least 10 characters.","claims":["Optional array of explicit claims"],"evidence":["Optional array of evidence items"]}
Dimensions:
substance_score: Shannon entropy on word frequencies (lexical diversity)
specificity_score: Density of concrete, quantitative markers
hedge_density: Proportion of hedging language (lower is better)
structure_score: Presence of claim->evidence->conclusion pattern
overall_score: Weighted average (substance 0.3, specificity 0.3, 1-hedge 0.2, structure 0.2)
Returns the weakest dimension with targeted improvement advice.
Optionally pass "context" with prior iteration data for escalation and stall detection.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"response_text": "<response_text>"
},
"name": "score_response_quality"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| claims | No | Optional explicit claims to check for | |
| context | No | Optional caller-provided context for iterative enforcement. Include prior failure counts, iteration history, and previous response data to enable escalation and stall detection. Omit for one-shot usage. | |
| evidence | No | Optional evidence items to check for | |
| response_text | Yes | The response text to evaluate (min 10 characters) |