Recipe catalog / tone-check
Check writing criteria
Check a draft against each supplied writing criterion.
You want to check a draft against a supplied set of writing criteria.
Explore this recipe interactively ยท Source and implementation guide
Use tone-check in TypeScript
Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.
import { toneCheck } from 'jev-recipes/tone-check';
const result = await toneCheck({
"draft": "You caused this problem. Read the manual.",
"criteria": [
{
"id": "blame",
"text": "Avoid blaming the customer."
}
]
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| draft | string | Required |
| criteria | array | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"draft": {
"type": "string"
},
"criteria": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"text": {
"type": "string"
}
},
"required": [
"id",
"text"
]
}
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"draft",
"criteria"
]
},
"result": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"model": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"input_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"input_tokens",
"output_tokens"
],
"additionalProperties": false
},
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"allPassed": {
"type": "boolean"
},
"checks": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"pass",
"fail",
"unclear"
]
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"probabilities": {
"type": "object",
"propertyNames": {
"type": "string",
"enum": [
"pass",
"fail",
"unclear"
]
},
"additionalProperties": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"required": [
"pass",
"fail",
"unclear"
]
}
},
"required": [
"id",
"status",
"verdict",
"confidence",
"probabilities"
],
"additionalProperties": false
}
}
},
"required": [
"model",
"usage",
"status",
"allPassed",
"checks"
],
"additionalProperties": false
}
}Saved example result
This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo tone-check.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"allPassed": false,
"checks": [
{
"id": "blame",
"status": "ready",
"verdict": "fail",
"confidence": 0.96,
"probabilities": {
"pass": 0,
"fail": 1,
"unclear": 0
}
}
]
}
Evaluation evidence
No verified live accuracy measurement is available. Evaluate representative cases before using this decision in your workflow.
Use the evaluation guide to measure this decision on your own labeled cases.
Limitations
- Checks supplied writing criteria. It does not rewrite text, determine factual accuracy, or check exact character counts.
- Supply 1 to 50 items per list, each with a unique non-empty ID and non-empty text.
Related recipes
- draft-compare: Use draft-compare to choose between two drafts under a rubric.