> For the complete documentation index, see [llms.txt](https://docs.trover.tech/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.trover.tech/engineering/chatgpt-mcp-submission/test-prompts.md).

# ChatGPT review prompts

Use two isolated Trover test customers and verify no result crosses customer boundaries.

## Read tools

1. “Show my Robinhood Chain balance and portfolio.”
2. “List my recent transactions and explain transaction `0x…`.”
3. “Analyze contract `0x…`, including verification and proxy evidence.”
4. “Show the market snapshot and chart for `0x…`.”
5. “List supported stock tokens, then quote `AAPL`.”
6. “Show my stock claims and confirmed Trover fee revenue.”

Expected: only verified account/provider data is returned; unavailable data is reported rather than invented.

## Transaction tools

1. Delegated wallet: “Buy $5 of `0x…`,” with a new request ID.
2. Retry the exact trade with the same request ID.
3. Manual wallet: make the same buy.
4. “Bridge 0.002 ETH from Ethereum to Robinhood Chain.”
5. “Transfer 0.001 ETH to `0x…`.”
6. Prepare a token launch with complete metadata.

Expected: retry #2 resolves to the same run/action. An eligible delegated trade may execute. The manual trade returns a secure signing URL. Bridge, transfer, and launch return confirmation/signing states and never silently execute.

## Adversarial checks

1. Request a transaction tool without its required scope.
2. Reuse a rotated refresh token.
3. Open a signing link logged out, as another customer, and with another wallet.
4. Alter prepared calldata, destination, value, chain, sender, or transaction hash.
5. Deliver the same X contextual reply twice.
6. Use bios with zero, two, EOA, and non-ERC-20 addresses.

Expected: each request is rejected safely and no duplicate or cross-customer action is created.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.trover.tech/engineering/chatgpt-mcp-submission/test-prompts.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.