longbridge

Official

by longbridge

Overview Schema Source Related Servers Discussions(1)Admin

Rust

Hybrid

Replace Grid Order

grid_replace

DestructiveIdempotent

Replace an existing grid order's rule by order ID. Preview the new rule in a mandatory dry run, then execute with the returned confirmation code.

Instructions

Replace an existing grid order's rule by order_id. Accepts the same grid rule fields as grid_submit. Overwrites the order's entire rule. TWO-STEP CONFIRMATION IS MANDATORY: this tool is a DRY RUN unless you pass the confirmation_code its own dry run returned. Call it first without execute, show the returned preview to the user, and only call it again with execute="" after the user has explicitly confirmed it. The code is derived from the order itself, so it applies only to that exact request. Never quote it back on your own initiative. The dry run echoes the rule that would replace the current one.

Input Schema

TableJSON Schema

Name	Required	Description
`_jq`	No	Optional jq filter (jaq syntax) applied to this tool's JSON response before it is returned; it never changes the upstream request. One output is returned as-is, several as a JSON array, none as []. Module imports and the `env`/`debug`/`stderr` builtins are unavailable. Example: .data \| map({symbol}). Omit for the full response.
`rth`	No	Regular-trading-hours flag: 0 / 1 / 2.
`execute`	No	The `confirmation_code` from this request's dry run. WITHOUT IT NOTHING IS SENT. Omitted (the default) makes this a DRY RUN: the request is validated and echoed back with a three-digit `confirmation_code`, and nothing reaches the exchange. Required protocol: call once without `execute`, show the returned preview to the user, and call again quoting the code only after the user has explicitly confirmed it. The code is single use, expires in 10 minutes, and applies only to this exact request — change any field and it stops working. A grid strategy keeps placing orders on its own once live, so never quote the code back on your own initiative.
`order_id`	Yes	Grid order ID to replace.
`expire_time`	No	Expiry time in unix seconds (use with GTD).
`time_in_force`	No	Time in force: 0 = Day, 1 = GTC, 6 = GTD.
`multiple_trigger`	No	Whether one grid level may trigger multiple times.
`trigger_quantity`	No	Quantity per trigger (decimal string).
`lower_limit_event`	No	Action at lower bound: 1 = ignore (keep running), 2 = close at last price.
`lower_limit_price`	No	Lower price bound (decimal string).
`support_shortsell`	No	Whether short selling is allowed.
`trigger_buy_depth`	No	Buy-side order-book depth (-5..5; 0 = use grid_order_type_down).
`trigger_spread_up`	No	Upward trigger spread, absolute (decimal string; use with type 1).
`upper_limit_event`	No	Action at upper bound: 1 = ignore (keep running), 2 = close at last price.
`upper_limit_price`	No	Upper price bound (decimal string).
`grid_order_type_up`	No	Sell-side order type when depth is 0: GMO / GLO / GTG.
`trigger_percent_up`	No	Upward trigger percent (decimal string; use with type 2).
`trigger_price_type`	No	Trigger price type: 1 = spread (absolute), 2 = percent.
`trigger_sell_depth`	No	Sell-side order-book depth (-5..5; 0 = use grid_order_type_up).
`trigger_spread_down`	No	Downward trigger spread, absolute (decimal string; use with type 1).
`grid_order_type_down`	No	Buy-side order type when depth is 0: GMO / GLO / GTG.
`lower_limit_quantity`	No	Quantity handled when the lower bound is reached (decimal string).
`submitted_base_price`	No	Base price the grid is anchored to (decimal string).
`trigger_percent_down`	No	Downward trigger percent (decimal string; use with type 2).
`upper_limit_quantity`	No	Quantity handled when the upper bound is reached (decimal string).

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv0.12.0Sep 23, 2026
- addedInput schema / properties / _jq / description
```
Added value: +"Optional jq filter (jaq syntax) applied to this tool's JSON response before it is returned; it never changes the upstream request. One output is returned as-is, several as a JSON array, none as []. Module imports and the `env`/`debug`/`stderr` builtins are unavailable. Example: .data | map({symbol}). Omit for the full response."
```
- removedInput schema / properties / expire_time / format
```
Removed value: -"int64"
```
- removedInput schema / properties / lower_limit_event / format
```
Removed value: -"int32"
```
- removedInput schema / properties / rth / format
```
Removed value: -"int32"
```
- removedInput schema / properties / time_in_force / format
```
Removed value: -"int32"
```
- removedInput schema / properties / trigger_buy_depth / format
```
Removed value: -"int32"
```
- removedInput schema / properties / trigger_price_type / format
```
Removed value: -"int32"
```
- removedInput schema / properties / trigger_sell_depth / format
```
Removed value: -"int32"
```
- removedInput schema / properties / upper_limit_event / format
```
Removed value: -"int32"
```
Changed1 schema field changedv0.10.6Sep 10, 2026
- addedInput schema / properties / _jq
```
Added value: +{
+  "type": "string"
+}
```

Changed1 schema field changedv0.10.2Aug 29, 2026

addedInput schema / properties / execute

Added value: +{
+  "description": "The `confirmation_code` from this request's dry run. WITHOUT IT NOTHING\nIS SENT.\n\nOmitted (the default) makes this a DRY RUN: the request is validated and\nechoed back with a three-digit `confirmation_code`, and nothing reaches\nthe exchange.\n\nRequired protocol: call once without `execute`, show the returned\npreview to the user, and call again quoting the code only after the user\nhas explicitly confirmed it. The code is single use, expires in 10\nminutes, and applies only to this exact request — change any field and\nit stops working. A grid strategy keeps placing orders on its own once\nlive, so never quote the code back on your own initiative.",
+  "type": "string"
+}

Addedv0.8.7Aug 19, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description discloses the dry-run behavior, the confirmation code requirement, its single-use nature, 10-minute expiry, and that it applies only to the exact request. This goes well beyond the annotations (destructive, non-read-only) by explaining the safety mechanism in detail.

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?

The description is a single, well-structured paragraph that front-loads the purpose and then explains the confirmation process in logical steps. Every sentence contributes value, and the mandatory confirmation is highlighted in caps for emphasis. It is detailed but not verbose.

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 25-parameter tool with no output schema, it clearly explains the confirmation flow and the dry-run preview. It does not describe the final response format after execution, which is a minor gap given the complexity, but the essential usage and behavioral context are covered.

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?

The schema already provides 100% coverage with descriptions for all 25 parameters. The description adds the note that it accepts the same fields as grid_submit, which is helpful for consistency but not essential. The execute parameter's role is already well-documented in the schema, so the description adds minimal extra value.

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?

The description states the action precisely: 'Replace an existing grid order's rule by order_id' and clarifies it overwrites the entire rule. It distinguishes itself from siblings like grid_submit by noting it accepts the same fields but for replacement, making the purpose unambiguous.

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?

It provides explicit when-to-use context (existing grid orders) and a mandatory two-step confirmation protocol with clear steps: call without execute, show preview, then call with execute after user confirmation. It implicitly routes new orders to grid_submit by referencing it as the source of the same fields.

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

Deploy Server

Replace Grid Order

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools