# Forecast clicks and cost for a keyword list

> Tier: recipe. Operating recipe: real tool sequence, core rules, known traps.

Forecast metrics for a candidate list, read with their assumptions attached.

**Intent.** What a keyword list would buy at a bid level, from Google's forecast.

## When to use

- Budgeting a new theme.
- A client asks 'what would it cost to be on X'.

## When not to use

- Long-horizon promises: forecasts describe the current auction only.

## Sources

Required: Google Ads

## Preconditions

- The account is ticked in the dashboard, confirmed via list_accounts.

## Inputs

- `window`: Analysis window. Default: last 30 days.

## Procedure

1. Run the forecast on the list at intended bids. — tools: `google_ads_generate_keyword_forecast_metrics`
2. Present cost and clicks with the assumption set.

## Decision rules

- **When** The forecast is quoted to a client → **conclude** Attach the auction-stability caveat in the same sentence, not a footnote.

## Evidence requirements

- Every figure carries its account, metric and window.
- Anything below a readable sample size is reported as unjudged, not as zero.

## Human approval boundary

- The readout changes nothing. Any change it motivates goes through Safe Writes: preview, human confirmation, then apply.

## Failure modes

- Forecasts ignore your ad quality: real CPCs land differently once Quality Score exists.

## Output

- **Readout**: The figures, with windows and accounts named.
- **Flags**: What deserves a deeper skill or a human decision.

## Related

- Skill: [keyword-expansion](https://www.getmcpads.com/skills/keyword-expansion.md)