TradeHub

Execute a previewed order

execute_previewed_order

DestructiveIdempotent

Execute a preview from preview_perp_order: re-checked at a fresh price, then sent to the exchange with its stop-loss placed there. Use only after a successful preview. Not for new or changed orders (preview again). If a person must approve (propose level, or no trade:execute scope) it waits; wait_seconds (0-30) holds the call open for the decision. Inputs: preview_id, client_order_id (idempotency key: repeating it returns the first result). A fill cannot be undone; the remedy is close_perp_position_reduce_only. Next: get_order_request_status(request_id) while pending.

Input Schema

Name	Required	Description
`preview_id`	Yes	From preview_perp_order, within 30 seconds
`wait_seconds`	No	If the order needs a person's approval, wait up to this long for the decision before returning
`client_order_id`	Yes	Your idempotency key, unique per agent; repeating it returns the first result instead of a second order

Output Schema

Name	Required	Description
`ok`	Yes	False when rejected or failed
`fee`	No	Once executed: the trading fee, estimated at once and replaced by the amount the exchange charged once its fill records show it
`legs`	No	A ladder entry: per leg {price, size_base, order_id, sl_oid, status}; status resting, or after a refused leg withdrawn, filled or partly_filled
`error`	No	Why it was rejected or failed
`venue`	No	Venue name
`checks`	No	Checks run at execution
`sl_oid`	No	Venue order id of the protective stop
`status`	Yes	pending_approval, armed (a trigger entry waiting for its price), executed, rejected, failed, expired, declined, cancelled, or executing (TradeHub has not confirmed the outcome yet: check get_order_request_status)
`receipt`	No	Signed receipt (compact JWS, EdDSA) once executed: request, checks, preview price, fill, slippage, order ids, delegation. Verify with /.well-known/tradehub-receipts.jwks
`order_id`	No	Venue order id of the fill
`fill_price`	No	Average fill, USD per coin
`request_id`	Yes	Order request id; get_order_request_status(request_id) follows it
`deprecation`	No	Present only while this tool is deprecated: replacement, removal_date, changelog
`filled_size`	No	Filled size, in the base coin (e.g. BTC), not USD
`take_profits`	No	set_take_profit_levels: the take-profits now on the exchange
`trigger_price`	No	status armed: opens at market when the mark reaches this, USD per coin
`trigger_expires_at`	No	status armed: when it lapses unless reached, ISO 8601 UTC
`approval_expires_at`	No	While pending: when the approval request lapses, ISO 8601 UTC

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

addedOutput schema / properties / legs

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "A ladder entry: per leg {price, size_base, order_id, sl_oid, status}; status resting, or after a refused leg withdrawn, filled or partly_filled",
+  "title": "Legs"
+}

Changed2 schema fields changedOct 27, 2026

addedOutput schema / $defs / FeeOut

Added value: +{
+  "additionalProperties": true,
+  "properties": {
+    "actual": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The charged amount in asset; negative = a rebate",
+      "title": "Actual"
+    },
+    "actual_usd": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "What the exchange charged, USD; null until its fill records show it (or when charged in another asset, see actual and asset)",
+      "title": "Actual Usd"
+    },
+    "asset": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The asset it was charged in (USDT, USDC, BNB …)",
+      "title": "Asset"
+    },
+    "deprecation": {
+      "anyOf": [
+        {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "Present only while this tool is deprecated: replacement, removal_date, changelog",
+      "title": "Deprecation"
+    },
+    "estimated_usd": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The account's rate x the filled notional, USD",
+      "title": "Estimated Usd"
+    },
+    "kind": {
+      "description": "open or close",
+      "title": "Kind",
+      "type": "string"
+    },
+    "status": {
+      "description": "pending (not read yet), done, or unknown (the exchange never showed it)",
+      "title": "Status",
+      "type": "string"
+    }
+  },
+  "required": [
+    "kind",
+    "estimated_usd",
+    "actual_usd",
+    "actual",
+    "asset",
+    "status"
+  ],
+  "title": "FeeOut",
+  "type": "object"
+}

addedOutput schema / properties / fee

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/FeeOut"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Once executed: the trading fee, estimated at once and replaced by the amount the exchange charged once its fill records show it"
+}

First observedOct 27, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag destructive/openWorld/idempotent, but the description adds substantive context beyond them: the order is re-checked at a fresh price, the stop-loss is placed at the exchange, a human approval path may block, wait_seconds bounds that wait to 0-30s, and a fill is irreversible with close_perp_position_reduce_only as the remedy. That is exactly the kind of risk and side-effect detail annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and the safety-critical 'cannot be undone' note, and every sentence carries new information. The heavy parenthetical style and fragment sentences make it dense to parse, which keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, human-approval-gated execution tool it covers prerequisites, the approval flow, timeout bounds, idempotency, irreversibility with a remedy, and the next polling call. An output schema exists, so return-value detail is correctly omitted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3; the description earns an extra point by framing preview_id as freshness-bound and client_order_id as an idempotency key whose repetition returns the first result rather than placing a second order. Much of this duplicates the schema text, so it stops short of 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Execute a preview from preview_perp_order') and immediately scopes it: re-priced then sent to the exchange with the stop-loss placed there. It explicitly distinguishes itself from the preview sibling and from order creation, so an agent can pick it over preview_perp_order or amend_open_entry_order without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives hard preconditions ('Use only after a successful preview'), an explicit exclusion ('Not for new or changed orders (preview again)'), and a follow-up path ('Next: get_order_request_status(request_id) while pending'). It also explains the approval branch and how wait_seconds selects between waiting and returning immediately.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All TradeHub tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?