Use this when the user asks to cancel a resting or trigger order by its oid (from get_my_open_orders).
| Name | Required | Description | Default |
|---|---|---|---|
| order_id | Yes | The Hyperliquid order id (oid) to cancel — see get_my_open_orders |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description clarifies the tool targets resting or trigger orders and that the oid comes from get_my_open_orders, adding some context beyond the annotations. It does not contradict the destructiveHint and idempotentHint annotations, though it does not elaborate on consequences or failure behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence fully conveys the purpose, target order type, and required identifier source with no wasted words. The condition is front-loaded, making it easy for an agent to scan and apply.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simple one-parameter interface and annotations already indicating destructive, non-idempotent behavior, the description is nearly complete. It explains what to cancel and where the oid comes from; only a brief note on expected outcome or error cases would make it fully self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already fully documents the single required parameter, including its type and source. The description adds no new parameter semantics beyond restating what the schema provides, so the schema-heavy baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('cancel'), a precise resource ('resting or trigger order'), and the required identifier source ('oid from get_my_open_orders'). This clearly distinguishes it from sibling tools like place_order and close_position.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this when the user asks to cancel a resting or trigger order', providing a clear condition for invocation. However, it does not mention alternatives or explicitly state when not to use this tool versus siblings like close_position.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool maps to a distinct resource/action: market data, account state, resting orders, audit records, fills, order placement, and risk management. The only close pair, preview_order and place_order, is clearly delineated as validation vs execution.
All tool names follow a consistent snake_case verb_noun pattern (get_, place_, cancel_, close_, set_). The object names are uniform and predictable, making the set easy to navigate.
13 tools is well-scoped for a trading server: market data, account/order queries, execution, and position risk each have coverage without redundancy or bloat.
The surface covers the core trading lifecycle: market data, account, preview/place/cancel, close position, TP/SL, and historical records. Minor gaps exist (e.g., no modify-order operation and no standalone position detail endpoint), but agents can work around them via cancel/replace and get_my_account.