Skip to main content
Glama
longbridge

longbridge

Official

Submit Order

submit_order
Destructive

Submit buy or sell orders through a two-step process: generate a dry-run preview first, then execute using the returned single-use confirmation code.

Instructions

Submit a buy/sell order. DRY RUN unless execute is the confirmation_code from its own dry run: call once without execute, show the preview to the user, then re-call quoting the code only after they explicitly confirm.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sideYesBuy or Sell
remarkNoOrder remark (max 255 characters)
symbolYesSecurity symbol, e.g. "700.HK"
executeNoThe `confirmation_code` from this order'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 that exact order. The code is single use, expires in 10 minutes, and applies only to this exact order — change any field and it stops working. Never quote it back on your own initiative, and never in the same turn the user first asks.
order_typeYesOrder type (HK supports all; US supports LO/MO/LIT/MIT/TSLPAMT/TSLPPCT only): - LO (Limit Order): requires submitted_price - ELO (Enhanced Limit Order, HK only): requires submitted_price - MO (Market Order): no price required - AO (At-auction Order, HK only): executed at auction price, no price required - ALO (At-auction Limit Order, HK only): requires submitted_price - ODD (Odd Lots Order, HK only): requires submitted_price, for non-standard lot sizes - LIT (Limit If Touched): requires submitted_price and trigger_price; activates when market price touches trigger_price - MIT (Market If Touched): requires trigger_price only; executes at market when trigger_price is touched - TSLPAMT (Trailing Limit If Touched by Amount): requires trailing_amount and limit_offset; trailing stop by fixed amount - TSLPPCT (Trailing Limit If Touched by Percent): requires trailing_percent (0-1) and limit_offset; trailing stop by percentage - SLO (Special Limit Order, HK only): requires submitted_price; cannot be replaced after submission
expire_dateNoExpiry date (yyyy-mm-dd). Required when time_in_force is GTD
outside_rthNoOutside regular trading hours: "RTH_ONLY" (regular trading hours only), "ANY_TIME" (any time including pre/post market), "OVERNIGHT" (overnight session, US only)
limit_offsetNoLimit offset from the trailing stop price. Required for: TSLPAMT, TSLPPCT
time_in_forceYesOrder validity: "Day" (Day Order, expires end of session), "GTC" (Good Til Canceled), "GTD" (Good Til Date, requires expire_date)
trigger_priceNoTrigger (activation) price. Required for: LIT, MIT, TSLPAMT, TSLPPCT
submitted_priceNoLimit price. Required for: LO, ELO, ALO, ODD, LIT, SLO
trailing_amountNoTrailing amount (absolute price distance). Required for TSLPAMT
trailing_percentNoTrailing percent as decimal (e.g. 0.05 = 5%). Required for TSLPPCT
submitted_quantityYesOrder quantity (number of shares)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dry_runYes
previewNo
order_idNo
next_stepNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed6 schema fields changedv0.10.2
    • addedInput schema / properties / execute
      Added value: +{
      +  "description": "The `confirmation_code` from this order's dry run. WITHOUT IT NOTHING IS\nSENT.\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 that exact order. The code is single use,\nexpires in 10 minutes, and applies only to this exact order — change any\nfield and it stops working. Never quote it back on your own initiative,\nand never in the same turn the user first asks.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / dry_run
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / next_step
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / order_id / type
      Previous value: -"string"New value: +[
      +  "string",
      +  "null"
      +]
    • addedOutput schema / properties / preview
      Added value: +{}
    • changedOutput schema / required
      Previous value: -[
      -  "order_id"
      -]New value: +[
      +  "dry_run"
      +]
  2. Changed1 schema field changedv0.7.1
    • removedInput schema / title
      Removed value: -"SubmitOrderParam"
  3. Changed4 schema fields changedv0.6.0
    • removedOutput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • removedOutput schema / description
      Removed value: -"Returned by `submit_order`."
    • removedOutput schema / properties / order_id / description
      Removed value: -"The newly-created order ID. Pass this to `cancel_order` /\n`replace_order` / `order_detail`."
    • removedOutput schema / title
      Removed value: -"OrderIdResponse"
  4. Addedv0.4.5
  5. Removedv0.4.0
  6. Addedv0.3.2
  7. Removedv0.3.1
  8. First observedv0.1.12

TDQS

A4.3/5.0
Behavior5/5

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

The description fully discloses the safety-critical behavior: without execute nothing is sent, and with the code the order goes live. It goes well beyond the destructiveHint annotation by detailing the single-use confirmation code, 10-minute expiry, exact-order binding, and the ban on self-initiated confirmation.

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 top-level description is two dense sentences that front-load the most important operational fact: 'DRY RUN unless execute is the confirmation_code.' Detailed field explanations are correctly delegated to the schema, so no sentence is wasted.

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 14-parameter, destructive tool, the description plus schema covers the full invocation protocol, user-confirmation requirement, code expiry, and field-level constraints. An output schema exists, so return-value documentation is appropriately not required here.

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%, and the schema's per-field descriptions are already rich, especially the execute field explaining the dry-run protocol. The top-level description adds no additional parameter-level semantics beyond what the schema already provides, so the baseline score applies.

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

Purpose4/5

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

The description starts with the precise action 'Submit a buy/sell order' and clearly frames the dry-run/live distinction. It does not explicitly position itself against related sibling tools like cancel_order or replace_order, so it misses the full differentiation bar.

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?

It provides a concrete invocation protocol: call once without execute, show the preview, and re-call only after explicit confirmation. It also includes clear prohibitions such as 'Never quote it back on your own initiative' and 'never in the same turn the user first asks,' though it never names alternative order-management tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/longbridge/longbridge-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server