> For the complete documentation index, see [llms.txt](https://docs.djzs.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.djzs.ai/reference/verify-perp-trade.md).

# verify\_perp\_trade

Checks a perpetual or spot trade before it is placed. MCP tool on `https://mcp.djzs.ai/mcp`, 2.00 USDC per call over x402 on Base. Source: `djzs-trust-mcp/src/verify-perp-trade.ts`, registered in `djzs-trust-mcp/src/index.ts`.

The same check is available over HTTP as `POST /x402/verify_perp_trade` ([Paid check over HTTP](https://docs.djzs.ai/for-agents/paid-http.md)) and free as `POST /try/verdict` with `kind: "perp"` ([Free check](https://docs.djzs.ai/for-agents/free-check.md)).

## Input

| Field                                                               | Type                           | Notes                                                                                                                                                                                                                      |
| ------------------------------------------------------------------- | ------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `intent`                                                            | string, at least 10 characters | The trade in plain text: instrument, direction, size, leverage, entry, stop, target, venue, and the reason the price should move. A position sent with no reason fails.                                                    |
| `bracket`                                                           | object, optional               | Exact levels for a break-even calculation: `side` (`long` or `short`), `entry`, `stop`, `target`, `taker_fee_bps`, and optionally `hit_rate_pct`, `funding_rate_8h`, `sigma_annual`. Never enters the verdict or its hash. |
| `agent_address`                                                     | `0x` address, optional         | Adds this check to that agent's on-chain trust score. Permanent and public.                                                                                                                                                |
| `target_system`, `target_system_subject`, `target_system_signature` | optional                       | As on [verify\_pm\_trade](https://docs.djzs.ai/reference/verify-pm-trade.md): a certificate label, stored only with a valid signature.                                                                                     |

## Output, in scope

The same fields as [verify\_pm\_trade](https://docs.djzs.ai/reference/verify-pm-trade.md#output-in-scope), with these differences:

| Field                 | Notes                                                                                                                                                     |
| --------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `tool`                | `"verify_perp_trade"`                                                                                                                                     |
| `taxonomy.extraction` | `DJZS-X-LF-v1.2`                                                                                                                                          |
| `risk_score`          | Sum of the weights that fired. FAIL at 50. The live codes are S01, E01, I01 and X01 ([Rulesets](https://docs.djzs.ai/how-a-verdict-is-made/rulesets.md)). |
| `halt_reason`         | On WAIT, the unresolvable fields, plus what to state when the reason or the exit is missing.                                                              |
| `fail_reason`         | When S01 fired: the position was stated with no reason.                                                                                                   |
| `mechanics`           | `status: "not_scored"`, and with `bracket`, a `breakeven` block. Execution mechanics are reported beside the verdict, never inside it.                    |

How the verdict is decided, including why a bounded trade with a stated reason can PASS with some fields still unknown: [Verdicts](https://docs.djzs.ai/how-a-verdict-is-made/verdicts.md#the-rule-for-perp-and-spot).

## Output, out of scope

A prediction-market bet is refused here and **not charged**:

```json
{
  "schema_version": "DJZS-ENGINE-V2",
  "tool": "verify_perp_trade",
  "in_scope": false,
  "reason": "Perp-only tool: the intent extracted as a prediction-market thesis. Use verify_pm_trade.",
  "verdict": null
}
```

## What it does not read

The check reads the stated reasoning. It does not read the venue's live price, funding, open interest or liquidation levels.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.djzs.ai/reference/verify-perp-trade.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
