> ## Documentation Index
> Fetch the complete documentation index at: https://docs.learningcommons.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Meaning Directness

> Measure how literal or figurative a text's language is with the Conventionality evaluator, scoring text complexity for grades 3-12 informational text.

[Evaluator last updated August 27, 2026.](#evaluator-release-history)

<EarlyAccess isBreaking={false} />

## Overview

The Meaning Directness evaluator assesses how directly a text communicates its meaning. It analyzes whether language is literal and explicit or relies on figurative, abstract, or implied meaning that requires interpretation.

## At a glance

|                      |                                                                                                                                                                                                                                            |
| :------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Inputs**           | Informational text to evaluate and grade level                                                                                                                                                                                             |
| **Supported grades** | 3–12                                                                                                                                                                                                                                       |
| **Rubric**           | [Student Achievement Partners (SAP)](https://learnwithsap.org/) ↗'s [Qualitative Text Complexity Rubric for Informational Text](https://learnwithsap.b-cdn.net/app/uploads/2026/04/Qualitative-Text-Complexity-Rubric-Informational.pdf) ↗ |

The evaluator was built and validated using the model and temperature below (other configurations will produce different results and may have lower accuracy):

|                 |                                                   |
| :-------------- | :------------------------------------------------ |
| **Model used**  | Gemini 3 Flash preview (`gemini-3-flash-preview`) |
| **Temperature** | 0                                                 |

## Getting started

Follow the [Quickstart](/evaluators/getting-started/quickstart) to start using this evaluator:

| Access method             |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
| :------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Evaluators playground** | [View in Platform](https://platform.learningcommons.org/apps/evaluators/playground) ↗                                                                                                                                                                                                                                                                                                                                                                                                  |
| **SDK**                   | [Python](https://github.com/learning-commons-org/evaluators/blob/main/sdks/python/src/learning_commons_evaluators/evaluators/meaning_directness.py) ↗ and [TypeScript](https://github.com/learning-commons-org/evaluators/blob/main/sdks/typescript/src/evaluators/meaning-directness.ts) ↗                                                                                                                                                                                            |
| **GitHub**                | [Python notebook](https://github.com/learning-commons-org/evaluators/blob/main/evals/student-facing-text/ela-reading/meaning-directness/example_notebook.ipynb) ↗<br />Prompts ([`system.txt`](https://github.com/learning-commons-org/evaluators/blob/main/evals/student-facing-text/ela-reading/meaning-directness/system.txt) ↗ and [`user.txt`](https://github.com/learning-commons-org/evaluators/blob/main/evals/student-facing-text/ela-reading/meaning-directness/user.txt) ↗) |

## Inputs

| Input           | Description                                                                        | Required |
| :-------------- | :--------------------------------------------------------------------------------- | :------- |
| **Text**        | Informational text to evaluate<br />10 - 10,000 words (\< 1,200 words recommended) | Yes      |
| **Grade level** | Target student grade level                                                         | Yes      |

## Output

| Field                           | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
| :------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Complexity rating**           | <ul><li><strong>Slightly complex:</strong> Confirm generated text uses literal, grade-appropriate language<ul><li>Language is literal and explicit</li><li>Meaning is directly stated</li><li>Minimal use of abstract, symbolic, ironic, and/or figurative language</li><li>Almost entirely explicit, literal, and straightforward</li></ul></li><li><strong>Moderately complex:</strong> Check whether occasional figurative language fits instructional goals<ul><li>Mostly literal language with occasional figurative or implicit meaning</li><li>Occasional use of abstract, symbolic, ironic, and/or figurative language</li><li>Primarily explicit, literal and straightforward</li></ul></li><li><strong>Very complex:</strong> Plan scaffolding when figurative language is central to meaning<ul><li>Frequent figurative language or implied meaning requires interpretation</li><li>Frequent use of abstract, symbolic, ironic, and/or figurative language</li></ul></li><li><strong>Exceedingly complex:</strong> Flag texts that require heavy interpretive support before use<ul><li>Language relies heavily on abstraction, layered meaning, or sustained figurative expression</li><li>Pervasive use of abstract, symbolic, ironic, and/or figurative language</li></ul></li></ul> |
| **Reasoning**                   | Explanation of the rating based on language features                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
| **Meaning Directness features** | Specific language features driving complexity (for example, idioms, metaphors, irony, or implicit meaning)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
| **Grade context**               | Comparison of meaning directness demands with expectations for the provided grade                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
| **Instructional insights**      | Suggestions for scaffolding or teaching unconventional language features<br /><br />**Example**: Use meaning directness features, grade context, and reasoning together to identify which language features to pre-teach or clarify                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |

## Evaluator release history

| Date            | Changed              |
| --------------- | -------------------- |
| August 27, 2026 | Minor prompt updates |
| March 20, 2026  | First release        |