Rule reference · Clarity

Vague language

  • vague_language
  • warning in this example
  • Clarity
  • stage · Ambiguity detection

Fires when: "something", "stuff", "etc", "and so on".

"Mention the features and stuff like that" delegates the list to the model, which fills it with plausible but invented details. In product, legal, or support content that becomes a factual error.

Replace each placeholder with the actual items. If the list is genuinely open-ended, say so and bound it ("mention up to 3 of these features").

Example that triggers it

Write a product description for our water bottle that mentions the material, capacity, and stuff like that, etc.

warning Vague wording: "stuff", "etc", "and stuff".

Why it matters. Placeholders like "something" or "etc." ask the model to invent the missing specifics.

Fix. Replace each vague term with the concrete items you mean.

Quality 84/100 · 22 tokens · 3 findings

Fixed version

Write a 100-word product description for our water bottle. Mention the material (18/8 stainless steel), the capacity (750 ml), and the 24-hour cold retention. Return plain text.

Quality 97/100 (+13) · 40 tokens · 1 findings

Resolved by the fix

  • vague_language: Vague wording: "stuff", "etc", "and stuff".
  • missing_output_format: No output format is specified.

Scores, token counts (GPT-4.1 tokenizer), and findings on this page are computed by the engine when the site is built.

How it affects the score

Each finding subtracts a fixed penalty from 100: critical 30, warning 10, info 3. This rule counts against the Clarity dimension. See the scoring model for the full formula.

Checked in the same pipeline stage

All 20 rules →