nexus-exchange-mcp

Official

Overview Schema Source Related Servers Discussions Admin

preview_order

Simulate an order to see its margin, equity, and fee impact before placing it. Review projected portfolio changes without sending anything to the matching engine.

Instructions

Preview an order without submitting it: projects the margin, equity, and fee impact of the order. Takes the same arguments as create_order. Nothing reaches the matching engine. Requires API credentials.

Input Schema

TableJSON Schema

Name	Required	Description
`side`	Yes	Order side.
`size`	Yes	Order quantity in base units, as a positive decimal string (> 0).
`type`	Yes	Order type. `limit` and `market` are unconditional. `stop_limit` / `stop_market` fire when the mark price crosses `trigger_price` in the adverse direction (stop-loss); `take_profit_limit` / `take_profit_market` fire on the favorable direction. `trailing_stop` fires a market order once the mark retraces from its best-seen extreme by `trailing_offset_bps`; `trailing_limit` fires the same way but rests a limit order priced off the fire price by `limit_offset_bps`. Field requirements: limit-family (`limit`, `stop_limit`, `take_profit_limit`) require `price`; stop / take-profit types require `trigger_price`; trailing types require `trailing_offset_bps`.
`price`	No	Limit price as a positive decimal string (> 0). Required for limit-family orders (`limit`, `stop_limit`, `take_profit_limit`); must be omitted for market, stop_market, take_profit_market, and trailing orders (which are priced by the engine or computed at fire time).
`market_id`	Yes	Market id, e.g. "BTC-USDX-PERP".
`reduce_only`	No	If true, only reduces an existing position.
`time_in_force`	No	Time in force. Defaults to GTC for limit, IOC for market. `PostOnly` rejects the order if it would take liquidity on entry, guaranteeing it rests as a maker.
`trigger_price`	No	Trigger threshold as a positive decimal string (> 0). Required for stop and take-profit orders (`stop_limit`, `stop_market`, `take_profit_limit`, `take_profit_market`): the order activates once the mark price crosses it — adversely for stops, favorably for take-profits. Must be omitted for other order types.
`limit_offset_bps`	No	Fire-time limit-price offset in basis points (`trailing_limit` only; required together with `trailing_offset_bps`). The rested limit sits at fire_price * (1 + offset) for buys / * (1 - offset) for sells; 0 rests exactly at the fire price.
`trailing_offset_bps`	No	Trailing trigger offset in basis points (1 bp = 0.01%). Required for trailing orders (`trailing_stop`, `trailing_limit`); must be omitted otherwise. Fires once the mark price retraces from its best-seen extreme by this many bps (0 fires at the first evaluation).

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.2.0Aug 19, 2026

addedInput schema / properties / limit_offset_bps

Added value: +{
+  "description": "Fire-time limit-price offset in basis points (`trailing_limit` only; required together with `trailing_offset_bps`). The rested limit sits at fire_price * (1 + offset) for buys / * (1 - offset) for sells; 0 rests exactly at the fire price.",
+  "maximum": 9999,
+  "minimum": 0,
+  "type": "integer"
+}

changedInput schema / properties / price / description

Previous value: -"Limit price as a positive decimal string (> 0). Required for limit orders, ignored for market."New value: +"Limit price as a positive decimal string (> 0). Required for limit-family orders (`limit`, `stop_limit`, `take_profit_limit`); must be omitted for market, stop_market, take_profit_market, and trailing orders (which are priced by the engine or computed at fire time)."

addedInput schema / properties / trailing_offset_bps

Added value: +{
+  "description": "Trailing trigger offset in basis points (1 bp = 0.01%). Required for trailing orders (`trailing_stop`, `trailing_limit`); must be omitted otherwise. Fires once the mark price retraces from its best-seen extreme by this many bps (0 fires at the first evaluation).",
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / trigger_price

Added value: +{
+  "description": "Trigger threshold as a positive decimal string (> 0). Required for stop and take-profit orders (`stop_limit`, `stop_market`, `take_profit_limit`, `take_profit_market`): the order activates once the mark price crosses it — adversely for stops, favorably for take-profits. Must be omitted for other order types.",
+  "type": "string"
+}

changedInput schema / properties / type / description

Previous value: -"Order type."New value: +"Order type. `limit` and `market` are unconditional. `stop_limit` / `stop_market` fire when the mark price crosses `trigger_price` in the adverse direction (stop-loss); `take_profit_limit` / `take_profit_market` fire on the favorable direction. `trailing_stop` fires a market order once the mark retraces from its best-seen extreme by `trailing_offset_bps`; `trailing_limit` fires the same way but rests a limit order priced off the fire price by `limit_offset_bps`. Field requirements: limit-family (`limit`, `stop_limit`, `take_profit_limit`) require `price`; stop / take-profit types require `trigger_price`; trailing types require `trailing_offset_bps`."

changedInput schema / properties / type / enum

Previous value: -[
-  "limit",
-  "market"
-]New value: +[
+  "limit",
+  "market",
+  "stop_limit",
+  "stop_market",
+  "take_profit_limit",
+  "take_profit_market",
+  "trailing_stop",
+  "trailing_limit"
+]

AddedJul 16, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the absence of side effects ("Nothing reaches the matching engine"), the auth prerequisite ("Requires API credentials"), and what the call returns conceptually (margin, equity, fee impact). It does not mention rate limits or the exact structure of the projection, leaving a minor gap.

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

Conciseness5/5

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

Four short sentences, each load-bearing: purpose, output content, argument compatibility, side-effect guarantee, and auth requirement. The core purpose is front-loaded and nothing is repeated.

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

Completeness4/5

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

For a 10-parameter mutation-adjacent tool with no annotations and no output schema, the description supplies the essential behavior (no order submitted, credentials needed) and the argument-compatibility shortcut. It could say more about the shape of the preview response, but an agent has enough to call it correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so all ten parameters are already documented in the schema with enums, requirements, and conditional rules. The description adds only the meta-point that the argument set mirrors create_order, which is useful for reuse but not new per-parameter meaning. Baseline 3 applies.

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?

"Preview an order without submitting it" gives a specific verb and resource, and the follow-up names exactly what the projection contains (margin, equity, fee impact). It also implicitly distinguishes itself from create_order by noting it takes the same arguments and that nothing reaches the matching engine.

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

Usage Guidelines4/5

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

The description makes the use case clear: dry-run an order before submitting, mirroring create_order's arguments. It lacks an explicit "use this instead of create_order when ..." routing sentence and names no exclusion conditions, so it stops short of the top score.

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

Deploy Server

preview_order

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools