TEST-203 docs: polish onboarding API guide wording (#1379)

## Description

- Applies the three remaining technical-writer suggestions from #1344: clarify what generated simulations cannot verify, separate coverage-gap examples from configuration, and capitalize the quota-error explanation.
- Branched from the latest fetched `main` (`bff62d2`). Only three lines of the onboarding guide change.

## Testing Steps

- [x] Pinned Fern 5.151.1 check: 0 errors and the same 15 existing warnings.
- [x] `git diff --check` passes.
- [ ] Review the generated docs preview when available.

Author: scott-lowe-vapi

fern/observability/simulations-generate-api.mdx

@@ -77,7 +77,7 @@ You then run the suite with the existing [`POST /eval/simulation/run`](/observab
     }
     ```
 
-    Review the requirements and answer the open questions. A requirement tagged `assumption` is based on a guess. A requirement tagged `not-testable` describes behavior generated simulations can't verify, such as latency. A requirement tagged `voice-only` needs a [voice run](/test/voice-testing) with a call recording. Its checks are skipped in chat runs.
+    Review the requirements and answer the open questions. A requirement tagged `assumption` is based on a guess. A requirement tagged `not-testable` describes behavior that generated simulations can't verify, such as latency. A requirement tagged `voice-only` needs a [voice run](/test/voice-testing) with a call recording. Its checks are skipped in chat runs.
   </Step>
 
   <Step title="Revise the draft (optional)">
@@ -262,7 +262,7 @@ A requirement with no simulation covering it appears in `coverage.gaps` with one
 
 | Reason | What it means | What to do |
 | -- | -- | -- |
-| `not-testable` | The requirement can't be verified by a generated simulation with the assistant's current configuration, such as latency or an audio check without a recording. | Read the requirement's note. Change the configuration if possible, or test the behavior outside generated simulations. |
+| `not-testable` | A generated simulation can't verify the requirement with the assistant's current configuration. Examples include latency, or an audio check without a recording. | Read the requirement's note. Change the configuration if possible, or test the behavior outside generated simulations. |
 | `unmapped` | No planned scenario exercises the requirement, or its simulation was removed from the suite. | Reword the requirement as an observable behavior and generate a new suite, or add a simulation by hand. |
 | `failed` | Its scenario could not be generated or saved in time. | Edit the suite with `retryFailed: true`. |
 | `budget` | It didn't fit in one generation's time budget. | Edit the suite with `retryFailed: true`. |
@@ -363,7 +363,7 @@ The `409`, `429`, and quota-unavailable `503` responses carry a JSON body and a
 | `500` | The assistant, its tools, or the suite couldn't be read. | Retry. For generation and edits, retry with the same key. |
 | `502` | The model failed to generate a usable result. | Retry. For generation and edits, retry with the same key. |
 | `503` | Simulation generation is paused, or no AI tester personalities are configured. | Retry later. |
-| `503` | `SIMULATION_ONBOARDING_QUOTA_UNAVAILABLE`: the quota couldn't be enforced for a private-key request. | Wait `Retry-After` seconds (15), then retry. For generation and edits, keep the same key. |
+| `503` | `SIMULATION_ONBOARDING_QUOTA_UNAVAILABLE`: The quota couldn't be enforced for a private-key request. | Wait `Retry-After` seconds (15), then retry. For generation and edits, keep the same key. |
 | `504` | The request took too long. | Retry. For generation and edits, retry with the same key. A generation may still save. |
 
 ## Next steps