Skip to main content

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.

Evaluator last updated May 7, 2026.

​
At a glance

Input typeInformational text
Passage length200 words or more
Supported grades3–12
A text’s purpose is what it’s trying to do: inform, persuade, explain, describe, or entertain. The Purpose Evaluator assesses how clearly a text communicates its central purpose. It analyzes whether a text’s intent is explicitly stated, indirectly hinted at, or masked (e.g., A passage presents itself as neutral information but is really building a persuasive argument).

​
Model and prompt

For instructions on running the evaluator, see Running an evaluator.
Model usedgemini-3-flash-preview
Temperature0
PromptsView prompts ↗
Python notebookView notebook ↗
The prompt is optimized for the model mentioned above. If you use other models and parameters, the output accuracy and result will vary.

​
Inputs

RequirementSupportedRequired
Target grade levelAllows grade-specific complexity guidanceYes
Text typeInformational textYes

​
Output

FieldDescription
complexity_scorePurpose complexity level: slightly_complex, moderately_complex, very_complex, exceedingly_complex, or more_context_needed.
reasoningOverall and detailed explanation of the rating, citing specific text features and their impact on student comprehension.
adjustment_and_scaffoldingSuggestions for adjusting the text or scaffolding students to make it appropriate for the target grade.
recommended_use_casesInstructional opportunity recommendations for the passage’s purpose.

​
Interpreting results

The evaluator returns one of the following ratings, along with reasoning, to help you determine your best course of action.
RatingMeaning
Slightly complexThe purpose is explicitly stated and concrete. Readers can identify intent without inference.
Moderately complexThe purpose is mostly clear but may require some inference from context or supporting details.
Very complexThe purpose is hinted at or subtle. Readers must infer intent from how details are selected or organized.
Exceedingly complexThe purpose is masked or layered. The text appears to do one thing while actually doing another.
More context neededThe passage is too short to determine its purpose. Try a longer portion of the text, or a different text.
More complex ratings indicate a text requires more interpretation by readers. Purpose complexity isn’t inherently good or bad; it depends on the instructional goals. A text rated Very complex or Exceedingly complex may be ideal for teaching students to identify implicit or persuasive intent, while the same rating would signal a mismatch if the goal is content comprehension.
For an overall grade-level judgment that synthesizes all text complexity dimensions, see the Grade-Level Appropriateness Evaluator.

​
Accuracy and validation

This evaluator is provided as Early access.
Comprehensive accuracy measures are still evolving, and validation testing is ongoing.
The evaluator was optimized using 35 annotated passages from the CLEAR Corpus ↗ and validated through expert review of additional samples.
MetricResult
Complexity score accuracy84% agreement with expert annotations
Expert agreement70%
Reasoning soundnessAverage 3.7 / 5
Dataset sourceCLEAR Corpus ↗
Exceedingly complex texts aren’t common in lower grades and the benchmark dataset doesn’t include many examples of them. Use caution when applying this evaluator to higher grade levels where such texts are more frequent.

​
Evaluator release history

DateChanges
May 7, 2026First release.