Rule reference · Completeness
Missing objective
Fires when: No task keyword, imperative sentence, or question.
A prompt that only describes material ("our Q3 sales report, with revenue by country") leaves the model to guess whether you want a summary, an analysis, a critique, or a rewrite. Different runs guess differently.
Lead with one imperative verb that names the outcome: summarize, classify, extract, draft, compare. Everything else in the prompt then reads as context for that task.
Example that triggers it
Our quarterly sales report for the EMEA region, with revenue by country and the change from last quarter.
warning No clear objective or task was found.
Why it matters. Without an explicit task the model has to guess what outcome you want, which makes results inconsistent.
Fix. Start with the task as an imperative, e.g. "Summarize…", "Write…", "Classify…".
Quality 87/100 · 21 tokens · 2 findings
Fixed version
Summarize the quarterly sales report below for the EMEA leadership team in 5 bullet points, covering revenue by country and the change from last quarter.
<report>
{{report}}
</report>Quality 100/100 (+13) · 40 tokens · 0 findings
Resolved by the fix
missing_objective: No clear objective or task was found.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 Completeness dimension. See the scoring model for the full formula.
Other completeness rules
- Unclear reference: "this" or "the above" with nothing included to refer to.