> ## Documentation Index
> Fetch the complete documentation index at: https://developers.everflow.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Prompt Library

> Ready-to-use prompts for common performance marketing workflows with the Everflow MCP Server.

Copy any of these prompts directly into your MCP-connected AI client. They are designed to work with the Everflow MCP Server without any modification — just replace the placeholders in brackets.

<Accordion title="Tips for better results">
  * **Be specific about date ranges.** The agent performs better with explicit dates (`2026-04-01` to `2026-04-30`) than relative terms like "last month."
  * **Ask for one thing at a time** in complex investigations. Multi-step workflows are more reliable when each step is confirmed before the next.
  * **Use IDs when you have them.** Filtering by `offer_id` or `affiliate_id` is faster and more accurate than filtering by name.
  * **Specify currency and timezone** if your network has non-USD defaults or you're comparing across regions.
  * **Paginate explicitly** for large datasets. Ask the agent to "get the next page" or set `page_size` in your prompt when working through long lists.
</Accordion>

<Note>
  Start every new session with `get_account_info` or ask the agent to call it automatically. This confirms your default currency and timezone, which affects how reports and timestamps are interpreted.
</Note>

***

## Getting oriented

**Confirm your session context**

> "Call get\_account\_info and summarize my network name, default timezone, default currency, and whether I have limited affiliate scope."

**Explore what's available**

> "Call get\_entity\_schema with no type argument and list all entity types I can query, along with their available filters."

***

## Reporting & performance

**Daily summary**

> "Give me a performance summary for yesterday. Show total clicks, conversions, revenue, payout, and profit. Use my network's default timezone."

**Top offers this month**

> "What are my top 10 offers by revenue this month? Show offer name, clicks, conversions, CVR, revenue, and profit. Sort by revenue descending."

**Top affiliates this week**

> "List my top 10 affiliates by revenue for the past 7 days. Include clicks, conversions, payout, and EPC."

**Performance by country**

> "Break down last week's performance by country. Show clicks, conversions, CVR, revenue, and profit. Highlight any country with CVR below 1%."

**Compare this week to last week**

> "Compare this week's performance to last week across total clicks, conversions, revenue, and profit. What changed significantly?"

**Offer performance trend**

> "Show me daily performance for offer \[OFFER\_ID] over the past 30 days. Include clicks, conversions, payout, and revenue. Flag any days with an unusually high invalid click rate."

***

## Offers

**Offer readiness audit**

> "For offer \[OFFER\_ID], check whether caps are configured, targeting is set, and at least one affiliate has visibility. Tell me if it's ready to go live."

***

## Affiliates & partners

**Partner overview**

> "Give me a full overview of affiliate \[AFFILIATE\_ID]. Include their status, tier, labels, currency, account manager, and recent activity (last login, API usage, 7-day clicks and conversions)."

***

## Traffic & conversion investigation

**Diagnose a click**

> "Look up transaction ID \[TRANSACTION\_ID]. Tell me the offer, affiliate, timestamp, whether it was unique, the error code and its meaning, and whether it converted."

**Diagnose a conversion**

> "Look up conversion \[CONVERSION\_ID]. Give me the full picture: offer, affiliate, advertiser, payout, status, error code, click timestamp, sub parameters, and adv parameters."

**Find invalid clicks for an affiliate**

> "Run a performance report for affiliate \[AFFILIATE\_ID] between \[FROM] and \[TO] with dimensions=click\_error\_code. Show each error code, its count, and sort by count descending. Ignore error code 0 (accepted clicks)."

**Affiliate traffic quality**

> "Run a performance report for affiliate \[AFFILIATE\_ID] over the past 7 days with dimensions=date. For each day show gross\_clicks, invalid\_clicks, and the invalid rate. Flag any day where invalid clicks exceed 5% of gross clicks."

***

## Financial & billing

**Payout summary by affiliate**

> "What was the total payout by affiliate for \[MONTH]? Sort by payout descending and flag anyone over \$\[AMOUNT]."

**Unpaid invoices for an affiliate**

> "List all invoices for affiliate \[AFFILIATE\_ID] with status unpaid. Show amount billed, start and end date, and whether the invoice is payable."

<Note>
  The invoice entity type requires an `affiliate_id` filter — a network-wide invoice list is not supported. To find affiliates with outstanding invoices, run `list_affiliates` first, then query invoices per affiliate.
</Note>

**Invoice details for an affiliate**

> "Show all invoices for affiliate \[AFFILIATE\_ID] in \[YEAR]. Include status, billed amount, paid amount, balance, and paid date."

***

## Registered prompt resources

The MCP Server registers named prompt resources — predefined workflows that MCP clients can invoke by name using the [MCP `prompts/get` method](https://modelcontextprotocol.io/docs/concepts/prompts), distinct from freeform chat. Each prompt accepts structured arguments and is listed in the server's prompt catalog. Most users interact through the freeform prompts above; these are primarily useful when building automation or using clients with a native prompt browser.

### troubleshoot-click

Diagnose why a click was blocked or produced an error, step by step.

| Argument         | Required | Description                                    |
| ---------------- | -------- | ---------------------------------------------- |
| `transaction_id` | Yes      | The 32-character transaction ID to investigate |

### partner-health-check

Comprehensive health check on an affiliate partner — activity, traffic quality, and offer access.

| Argument       | Required | Description                            |
| -------------- | -------- | -------------------------------------- |
| `affiliate_id` | Yes      | The affiliate ID to analyze            |
| `days`         | No       | Look-back window in days (default: 30) |

### revenue-analysis

Analyze revenue performance for a date range, with optional period-over-period comparison.

| Argument  | Required | Description                                                  |
| --------- | -------- | ------------------------------------------------------------ |
| `from`    | Yes      | Start date (`YYYY-MM-DD`)                                    |
| `to`      | Yes      | End date (`YYYY-MM-DD`)                                      |
| `compare` | No       | Set to `true` to compare against the prior equivalent period |

### offer-launch-readiness

Audit whether an offer is configured correctly and ready to go live — checks caps, targeting, payout, and affiliate visibility.

| Argument   | Required | Description           |
| ---------- | -------- | --------------------- |
| `offer_id` | Yes      | The offer ID to audit |
