Skip to main content
Glama
Sign In
pathiel

pathiel

by Julian-dev28
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

get_orders

Read-only

Retrieve open or historical Hyperliquid orders by status, coin, or order ID to inspect trigger prices, size, and reduce-only flags; use it to verify a position's stop and target before cancelling.

Instructions

Get orders, one query per call. status=open (default): resting orders on every dex with order type (Stop Market, Take Profit Limit, Limit), trigger price, size and reduce-only flag; this is how to see a position's stop and target. status=history: filled and cancelled orders, newest first. oid or cloid looks up one order and overrides status. coin and limit narrow the list (limit default 100 open, 50 history, max 2000); address reads any wallet. Use before cancel_order (it needs the oid) and to check a position is protected. For executed trades use get_history. Needs a configured account or an address; with neither it returns {error, no_account: true}. Returns {count, orders[]: {coin, oid, side, sz, limitPx, triggerPx, orderType, reduceOnly}} or one order's status.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_orders"
  }
}

Input Schema

NameRequiredDescriptionDefault
oidNoOne order by order id (overrides status).
coinNoCoin: a main-dex perp by name (BTC, ETH) or a HIP-3 perp as dex:SYMBOL (xyz:GOLD, xyz:BRENTOIL).
cloidNoOne order by client order id, 0x + 32 hex (overrides status).
limitNoMost rows to return.
statusNoopen: resting now. history: filled and cancelled.open
addressNoAny 0x address to read instead of the configured account (read-only; needs no key).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.6.1

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true, and the description adds substantial context beyond that: one query per call, newest-first ordering for history, default and maximum row counts, the read-only address override, the {error, no_account: true} failure shape, and the exact result payload. This is a rare case where a read tool documents its failure mode and return shape explicitly.

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?

Every clause carries information — modes, defaults, prerequisites, error shape, return shape — with no filler. The single dense paragraph with parentheticals is slightly harder to scan than a bulleted breakdown would be, which is the only reason it falls short of 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 six-parameter read tool with no output schema, the description supplies everything an agent needs: mode semantics, defaults and caps, prerequisite and failure behavior, ordering, and the returned field list. No meaningful gap remains for correct invocation.

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 the baseline would be 3, but the description adds real meaning: the limit defaults (100 open / 50 history) and max of 2000 are absent from the schema, and it reinforces that oid/cloid override status and that address reads an arbitrary wallet without a key. The coin and oid/cloid semantics are largely restated from the schema, keeping it just under a 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?

Opens with a specific verb+resource ("Get orders") and immediately scopes the tool's behavior across status=open and status=history, naming the exact fields returned per mode. It also distinguishes itself from the sibling get_history by reserving executed trades for that tool.

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 concrete when-to-use rules: call before cancel_order because it supplies the oid, and use it to verify a position's stop/target are resting. It names the alternative for the adjacent need ("For executed trades use get_history") and states the precondition (configured account or address).

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

Deploy Server

Other Tools