Descriptive writing

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 6.1 — Give information gradually (default severity: warning)
Statement: In descriptive text, present information gradually and make sure each sentence contains only one subject. Do not pack multiple facts or ideas about different subjects into one sentence, since this forces the reader to re-read the text to understand it.
Detection criteria:
- Flag sentences that combine information about more than one subject or idea (for example, a system's identity, its function, its internal signal path, and a downstream data transmission all stated in a single sentence).
- Flag dense passages where a large amount of technical information is compressed into very few sentences, forcing the reader to parse several ideas at once.
- Check that each sentence has one clear subject; flag sentences that shift to a new subject partway through via a comma splice or an added clause.
Do NOT flag (non-violations):
- A sentence with a subordinate clause that only defines or qualifies its single subject (rather than introducing a different subject) is not a violation.
Example — Non-STE: "During the approach to the runway, deviation pointers in the course indicators give commands to fly up or down and left or right. This information comes from the VHF transceivers, which are part of the Instrument Landing System." -> STE: "The Instrument Landing System (the system) on the aircraft shows data that helps the pilot during the approach to the runway. This system shows the pilot the deviations from the localizer course and the glideslope path. During the approach to the runway, deviation pointers in the course indicators show the pilot in which direction the aircraft must go."

### Rule 6.2 — Use key words and key phrases to give your text a logical structure (default severity: warning)
Statement: Use key words and key phrases — the same terminology repeated exactly — to connect a sentence to the ideas introduced earlier in the paragraph (not necessarily only the immediately preceding sentence), and use approved connecting words or phrases (for example, "and," "but," "then," "thus," "as a result," "at the same time") as one method, among others, to signal how a sentence relates to an earlier one. This gives the text a logical, easy-to-follow structure.
Detection criteria:
- Flag a sentence that does not repeat a key word/phrase from an earlier sentence in the paragraph and does not otherwise signal its relationship to what came before — the rule's positive requirement is consistent key-word/key-phrase repetition and connector use, not merely avoiding ambiguity.
- Flag a term that was introduced earlier in the paragraph and is then referred to with different wording instead of being repeated exactly (this reinforces rule 1.11 at the level of paragraph flow).
- Flag a sentence expressing a result, contrast, addition, or simultaneous event that does not use an approved connecting word/phrase or repeated key term to signal that relationship.
- (Detector heuristic, non-normative) When triage capacity is limited, prioritize cases where the missing link makes the relationship genuinely unclear over purely stylistic gaps — but this does not redefine the rule itself as ambiguity-only.
Do NOT flag (non-violations):
- The first (topic) sentence of a new paragraph is expected to introduce new information and is not required to repeat a key word from the prior paragraph.
- A sentence that links back to an earlier sentence in the chain (not only the immediately preceding one) is compliant — exact key-word repetition in every adjacent pair is not mandatory.
- A short sequence of simple, self-explanatory sentences whose relationship is already clear from context does not need an explicit connecting word between every pair.
Example — Non-STE: "The Instrument Landing System (the system) on the aircraft shows data that helps the pilot during the approach to the runway. The unit displays the deviations from the localizer course and the glideslope path." -> STE: "The Instrument Landing System (the system) on the aircraft shows data that helps the pilot during the approach to the runway. This system shows the pilot the deviations from the localizer course and the glideslope path."

### Rule 6.3 — Write short sentences — maximum 25 words in descriptive text (default severity: error)
Statement: In descriptive writing, use a maximum of 25 words per sentence. Descriptive text is permitted a higher word count than procedural text because its subject matter is inherently more complex, but any sentence over the limit must still be split into shorter sentences.
Detection criteria:
- Count the words in each sentence of descriptive text and flag any sentence with more than 25 words.
- Within a flagged sentence, identify coordinated clauses joined by 'and,' 'which,' or a list of commas as likely split points.
Do NOT flag (non-violations):
- This 25-word limit is specific to descriptive text; do not apply it to procedural instruction steps, which have their own (lower) sentence-length limit.
Example — Non-STE: "A smartphone is a cellular telephone that has an integrated computer and many other functions, such as an operating system, internet browsing as well as the ability to run software applications." -> STE: "A smartphone is a cellular telephone that has an integrated computer and many other functions. It includes an operating system and an internet browser, and it can also operate software applications."

### Rule 6.4 — Use paragraphs to show related information (default severity: warning)
Statement: Structure descriptive text into paragraphs, where each paragraph opens with a topic sentence that states what the paragraph is about, and every following sentence explains or adds information related to that topic. A new paragraph signals to the reader that a new or different topic follows.
Detection criteria:
- Flag a paragraph that does not open with a clear topic sentence stating its subject — for example, one that opens with a supporting detail or a sentence that assumes context not yet established.
- Flag a single block of text covering multiple distinct pieces of related information that should instead be split into separate paragraphs, each with its own topic sentence.
- For each sentence after the first in a paragraph, check that it explains or adds information to that paragraph's topic sentence; flag any sentence that instead belongs to a different topic.
Example — Non-STE: "A lightning strike can cause damage to the aircraft at the attachment points. From the attachment points, the lightning strike usually goes aft through the structure and can cause a malfunction of the electrical and electronic systems. If a lightning strike occurs, the maintenance personnel must do an inspection of the aircraft for damage before the next flight." -> STE: "A lightning strike can cause damage to the aircraft. The damage usually occurs at the attachment points.

From the attachment points, the lightning strike usually goes aft through the structure of the aircraft. The high current of the lightning strike can cause damage to the mechanical systems of the aircraft. Thus, a permanent or a temporary malfunction of the electrical and electronic equipment and systems can occur.

If a lightning strike occurs, it is necessary to do an inspection of the aircraft for damage. The maintenance personnel must do this inspection before the next flight."

### Rule 6.5 — Make sure that each paragraph has only one topic (default severity: warning)
Statement: Each paragraph in descriptive text must cover exactly one topic. The topic sentence — usually containing a key word and/or a connecting word or phrase — states that topic, and every other sentence in the paragraph must relate to it; do not combine two or more distinct topics in the same paragraph.
Detection criteria:
- Identify the topic sentence of each paragraph, then check whether every subsequent sentence in that paragraph still relates to that same topic; flag paragraphs where a sentence introduces an unrelated topic.
- Flag a paragraph that cannot be summarized by a single topic statement because it actually covers two or more distinct subjects.
Do NOT flag (non-violations):
- A paragraph may cover several related sub-points as long as they are all part of one larger, singular topic — this is not a violation.
Example — Non-STE: "The Instrument Landing System (the system) on the aircraft shows data that helps the pilot during the approach to the runway. This system shows the pilot the deviations from the localizer course and the glideslope path. This data about deviations from the localizer course and glideslope path comes from two VHF transceivers. These transceivers transmit this data to Air Traffic Control." -> STE: "The Instrument Landing System (the system) on the aircraft shows data that helps the pilot during the approach to the runway. This system shows the pilot the deviations from the localizer course and the glideslope path.

This data about deviations from the localizer course and glideslope path comes from two VHF transceivers. These transceivers transmit this data to Air Traffic Control."

### Rule 6.6 — No paragraph may have more than six sentences (default severity: error)
Statement: Limit each paragraph in descriptive text to a maximum of six sentences. If a paragraph would require more than six sentences, divide it into two or more smaller paragraphs, each covering a distinct part of the topic.
Detection criteria:
- Count the sentences in each paragraph and flag any paragraph with more than six sentences.
- For a flagged paragraph, identify the point where the topic narrows or shifts, since that is the natural split point (see rule 6.5).
Do NOT flag (non-violations):
- How a vertical-list item counts toward sentence-length limits is governed by rule 8.4, not this rule — do not apply a separate list-counting assumption here.
Example — Non-STE: "The shut-off valve operates in the valve body (21). The valve body (21) has an aluminum alloy ball (27), a retaining ring (31), two seals (26), and a spring (25). The spring (25) holds the ball (27) in position to prevent internal leakage. The preformed packings (18), (2) and (30) are installed on the seals (26), the shaft (28), and in the valve body. They prevent external leakage. One of the two seals (26), on which the spring (25) operates, has the function of a relief valve. It operates when the pressure applied in the opposite direction is more than a set value." -> STE: "The shut-off valve operates in the valve body (21). The valve body (21) has an aluminum alloy ball (27), a retaining ring (31), two seals (26), and a spring (25).

The spring (25) holds the ball (27) in position to prevent internal leakage. The preformed packings (18), (2) and (30) are installed on the seals (26), the shaft (28), and in the valve body. They prevent external leakage. One of the two seals (26), on which the spring (25) operates, has the function of a relief valve. It operates when the pressure applied in the opposite direction is more than a set value."

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"
    }
  ]
}