Sentences

You are an expert reviewer applying the ASD-STE100 Simplified Technical English (STE) standard.

Evaluate the TEXT below against every rule listed under RULES. Apply each rule independently and flag every deviation you find.

RULES:
### Rule 4.1 — Write short and clear sentences (default severity: error)
Statement: Write short sentences with clear structure that give accurate instructions and information. In procedures, give instructions directly to the reader in the imperative form; in descriptive text, give each sentence only one topic and build up information gradually across the sentences that follow, and never write abstract statements that omit the accuracy the reader needs.
Detection criteria:
- Flag long, convoluted sentences that pack multiple sequential actions or unrelated clauses together instead of being broken into short, direct steps or single-topic sentences.
- In descriptive text, flag any sentence that contains more than one topic, subject, or idea.
- In procedures, flag descriptive-style or indirect phrasing used instead of a direct imperative instruction.
- Flag abstract statements that do not tell the reader the required action or specific fact (e.g. a bare requirement or a vague claim of change with no specifics).
Do NOT flag (non-violations):
- A sequence of short, single-topic sentences that each build on the previous one is the compliant pattern for descriptive text, not a violation.
Example — Non-STE: "To remove the cover assembly (9), first remove the four screws (10) that attach the cover (11) to the housing (12), and then, after taking the cover (11) off the housing (12), remove the preformed packing (13) and throw it away." -> STE: "Remove the cover assembly (9) as follows:
A. Remove the four screws (10) that attach the cover (11) to the housing (12).
B. Remove the cover (11) from the housing (12).
C. Remove and discard the preformed packing (13)."

### Rule 4.2 — Do not omit words or use contractions to shorten sentences (default severity: error)
Statement: Write every sentence with all of its parts — do not omit nouns, verbs, subjects, or articles to make the sentence shorter, and do not use contractions such as "don't" or "isn't". Omitted words and contractions make a sentence shorter but not easier to read, and can create ambiguity.
Detection criteria:
- Flag any contraction (don't, isn't, aren't, can't, won't, etc.); it must always be written as the full two-word form.
- Flag sentences with an omitted subject, verb, or noun that leaves the actor or action ambiguous (e.g. a conditional clause like "If installed, remove the shims" that does not state what is installed).
- Flag omitted articles before nouns where the omission creates ambiguity, especially between two coordinated nouns (e.g. "Remove the bolt and stop", where "stop" without an article could be misread as a verb).
Do NOT flag (non-violations):
- Omitting the article before all but the first noun in a long series, per rule 4.5, is a separate, permitted construction and not a violation of this rule.
Example — Non-STE: "Rotary switch to INPUT." -> STE: "Set the rotary switch to INPUT."

### Rule 4.3 — Use a vertical list for complex text (default severity: warning)
Statement: When a sentence would otherwise be long because it includes many items (such as parts, components, or documents) or many actions, present those items as a vertical list instead. Introduce the list with a colon, mark each item consistently (dash, bullet, letter, or number), start each item with an uppercase letter, and punctuate the items according to whether each is a full sentence.
Detection criteria:
- Flag a long sentence that strings together multiple items or steps with commas/"and" where a vertical list would clearly be easier to read and understand — the standard sets no specific item-count threshold, so judge by length/complexity and readability rather than a fixed number of items.
- In an existing vertical list, flag a missing colon at the end of the introductory clause before the first item.
- Flag inconsistent capitalization, incorrect end punctuation (a comma or semicolon at the end of an item, a missing period on a full-sentence item, a period on a non-full-sentence item, or a missing period after the last item), or a list that mixes procedural (imperative) and descriptive items together.
- Flag a vertical list where an item does not connect clearly and correctly back to the introductory clause before the colon.
Do NOT flag (non-violations):
- A list item that is not a full sentence correctly has no end-of-item period; only the final item in the list takes a period.
- A sub-list flattened into the main list at a single indentation level (rather than nested) is the compliant layout, not an error.
Example — Non-STE: "The wheel assembly comprises the tire, the tube, the spokes, the spoke fittings, the valve, and the hub." -> STE: "The wheel assembly has these parts:
- The tire
- The tube
- The spokes
- The spoke fittings
- The valve
- The hub."

### Rule 4.4 — Use connecting words and phrases to link related sentences (default severity: warning)
Statement: Use an approved connecting word (such as "and", "but", "then", "thus"), an approved connecting phrase (such as "as a result", "at the same time"), or a demonstrative adjective to link a sentence to the related idea in the sentence before it, giving descriptive text a logical structure and clarifying explanations that follow a work step or a safety instruction.
Detection criteria:
- In descriptive text, flag a sentence that lacks a connecting word/phrase or demonstrative-adjective link to the related idea in the sentence before it, unless the logical relationship is already unmistakable from wording alone — the positive requirement is to use these links, not merely to avoid ambiguity.
- In procedures or safety instructions, flag an explanatory sentence that lacks a connecting word or demonstrative adjective linking it back to the preceding work step, warning, or caution, unless the link is already unmistakable.
- Flag connecting words or phrases that are not approved in the STE dictionary in place of a simple approved connector.
- (Detector heuristic, non-normative) When triage capacity is limited, prioritize cases where the missing link makes the relationship genuinely unclear over cases where it is merely stylistically absent — but do not use this as a reason to skip the rule's positive requirement entirely.
Do NOT flag (non-violations):
- A short sequence of simple, self-explanatory imperative work steps does not need an explicit connecting word between every step.
- A related sentence whose logical relationship to the previous one is already obvious from context and wording is compliant without an explicit connector — connecting words/phrases are one method for showing a link, not a requirement on every adjacent pair.
Example — Non-STE: "Tag the disassembled parts. It will help you during the subsequent procedures." -> STE: "Tag the disassembled parts. This method will help you during the subsequent procedures."

### Rule 4.5 — Use an article or demonstrative adjective before a noun (default severity: error)
Statement: When applicable, use an article (the, a, an) or a demonstrative adjective (this, these) before a noun or multi-word noun to show its position in the sentence; do not omit it to shorten the text. Do not use an article before a noun in a general statement or abstract concept, and do not use a definite article before a noun that is followed by an alphanumeric identifier, since the identifier makes it a proper noun.
Detection criteria:
- Flag a noun or multi-word noun that is missing a required article or demonstrative adjective, where the omission leaves the sentence ambiguous or ungrammatical (e.g. "Turn shaft assembly" or "Data module tells you...").
- Flag a definite article placed before a noun that is immediately followed by an alphanumeric identifier (e.g. "the circuit breaker 36L7").
- In a series of items introduced by a single article, check whether the intended meaning is that a modifier or article applies to the whole series or only to the first item, and flag a mismatch between the article pattern used and the intended meaning.
Do NOT flag (non-violations):
- No article is required before a noun in a general statement or abstract concept (e.g. "Solvents can cause damage to paint.", "This software increases performance.").
- Using an article before only the first noun in a long series of items, to mean the article applies to the whole series, is correct STE style, not an omission error.
Example — Non-STE: "Turn shaft assembly." -> STE: "Turn the shaft assembly."

PROCESSING METHODOLOGY (apply in this order before judging any rule below):
1. classify-block-context -- Label each content block before evaluating any rule: procedural-work-step | warning | caution | note | descriptive-paragraph | vertical-list-item | title-or-heading | quoted-text | table-cell. Rules that depend on appliesTo/contextPrerequisites (see individual rule records) require this label; if the caller does not supply one, the checker must return 'context required' for those rules rather than guess.
2. protect-immutable-spans -- Identify spans that must not be altered and are exempt from word-choice rules (1.x, 9.x) and count as one word (rule 8.6): quoted text, titles/headings, placard/label text, alphanumeric identifiers, proper nouns of individuals/groups/organizations/geopolitical entities. The rule 8.1 semicolon prohibition and rule 1.14 spelling rule both carry a narrow exception for this protected text only -- an author-written semicolon or spelling choice outside a protected span is never exempt.
3. segment-sentences-and-lists -- Split each block into sentences on '.', '!', '?' boundaries, respecting protected spans (do not split inside quoted text or an abbreviation like 'a.m.'). For vertical lists (rule 4.3), the colon before the list has the effect of a period (rule 8.4): everything before the colon is one sentence, and each subsequent list item is a separate sentence for word-count purposes.
4. tokenize-and-apply-word-count-rules -- Tokenize each sentence into words, applying the count exceptions in this order: (a) a hyphenated group functioning as one adjective or one compound technical noun counts as one word (rule 8.7); (b) a number, a number+unit pair, an abbreviation, an alphanumeric identifier, quoted text, a title/heading/placard/label, or a proper noun counts as one word (rule 8.6); (c) parenthetical text counts as one word in the containing sentence, but also forms its own sentence for internal word-count purposes (rule 8.5).
5. apply-sentence-length-limits -- Compare the tokenized word count against the applicable limit from the block's context label (step 1): 20 words for procedural-work-step/warning/caution (rule 5.1), 25 words for note (rule 5.5) and descriptive-paragraph (rule 6.3). A block with no context label cannot be checked against a length rule with confidence; return 'context required'.
6. resolve-vocabulary -- For each remaining token (outside protected spans), resolve it against dictionary.json first, then against the configured termbase (termbase-schema.json) per its resolutionOrder, then against the technicalNounCategories/technicalVerbCategories examples in ste-rules.json rules 1.5/1.12 as supporting (not sufficient) evidence. An unresolved token is 'review required', never an automatic pass -- see rules 1.1-1.4, 1.6, 1.8, 3.1, 3.3, 3.7, 9.1-9.3.
7. apply-syntax-and-style-rules -- Apply the remaining grammar/style rules (voice, tense, punctuation, structure) to the classified, tokenized, vocabulary-resolved text.

Note: This spec covers deterministic mechanics only (segmentation, counting, protected text, resolution order). It does not replace the semantic judgment required by rules flagged manualReviewRequired in checkerPolicy (e.g. 1.8, 1.12, 4.3, 4.4, 6.2, 7.3) -- those still require an LLM call or human review per rule.

TEXT TO EVALUATE:
"""
<PASTE THE TEXT TO EVALUATE HERE>
"""

INSTRUCTIONS:
- Only flag violations of the rules listed above; never invent a rule id that is not listed.
- For every violation, "quote" must be an exact, verbatim substring copied from TEXT (so it can be located and highlighted).
- Use each rule's default severity unless the specific instance clearly warrants a different one (error = blocks compliance, warning = should be fixed, info = advisory).
- Do not report the same violation more than once, and do not flag a rule if TEXT already complies with it.
- If you are not confident a rule is actually violated, do not report it.

Respond with ONLY valid JSON (no markdown code fences, no commentary) matching this shape:
{
  "violations": [
    {
      "ruleId": "1.1",
      "quote": "exact text copied from TEXT",
      "message": "specific explanation of the deviation",
      "severity": "error",
      "suggestedFix": "a compliant replacement for the quoted text"
    }
  ]
}
If there are no violations, respond with {"violations": []}.

{
  "violations": [
    {
      "ruleId": "1.1",
      "quote": "exact text copied from TEXT",
      "message": "specific explanation of the deviation",
      "severity": "error",
      "suggestedFix": "a compliant replacement for the quoted text"
    }
  ]
}