TradeForAgents

Prepare order

prepare_order

Validate an order against risk limits and estimate fill price and fees. With dry_run: true nothing else happens. Otherwise returns typed_data to sign and a prepared_id for submit_signed_order (valid 120 s). Use when you sign transactions yourself.

Input Schema

TableJSON Schema

Name	Required	Description
`side`	Yes
`size`	No	Base-asset size. Give this or notional_usd.
`type`	No	market (default) or limit
`market`	Yes	Market symbol, e.g. BTC, ETH, SOL (see get_markets)
`dry_run`	No	true: only validate and estimate costs
`stop_loss`	No	Market orders on perps: reduce-only stop-loss that closes this position when the mark price crosses trigger_price
`limit_price`	No	Required for limit orders
`market_type`	No	perp (default) or spot; spot only for markets get_markets lists as spot
`reduce_only`	No
`take_profit`	No	Market orders on perps: reduce-only take-profit that closes this position when the mark price crosses trigger_price
`notional_usd`	No	Order value in USD. Give this or size.
`slippage_bps`	No	Market orders: max slippage vs mid in basis points (default 50)
`time_in_force`	No	Limit orders: gtc (default), ioc, alo (post-only)
`idempotency_key`	No	Optional. Reuse the same value when retrying the same operation so it is not executed twice.
`builder_approval`	No	Signed builder-fee approval; needed once before the first real order

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 20, 2026

addedInput schema / properties / stop_loss

Added value: +{
+  "description": "Market orders on perps: reduce-only stop-loss that closes this position when the mark price crosses trigger_price",
+  "properties": {
+    "trigger_price": {
+      "exclusiveMinimum": 0,
+      "type": "number"
+    }
+  },
+  "required": [
+    "trigger_price"
+  ],
+  "type": "object"
+}

addedInput schema / properties / take_profit

Added value: +{
+  "description": "Market orders on perps: reduce-only take-profit that closes this position when the mark price crosses trigger_price",
+  "properties": {
+    "trigger_price": {
+      "exclusiveMinimum": 0,
+      "type": "number"
+    }
+  },
+  "required": [
+    "trigger_price"
+  ],
+  "type": "object"
+}

First observedOct 20, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations provide only readOnlyHint=false, so the description carries most of the burden — and it delivers real behavior: dry_run short-circuits, the normal path returns typed_data plus a prepared_id with a 120 s validity window. It omits auth requirements, failure modes when risk limits are breached, and what happens after expiry.

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?

Three sentences, each earning its place: purpose, dry_run branch, then return payload and TTL. Front-loaded with the core action and no filler.

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?

With no output schema, the description correctly explains the return payload (typed_data, prepared_id, 120 s TTL), which is the critical missing piece for a 15-parameter preparation tool. It leaves some gaps around error behavior and the one-time builder_approval prerequisite, which lives only in the schema.

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 87%, so the schema already documents nearly all 15 parameters including nested builder_approval and stop/take-profit objects. The description only touches dry_run and implicitly the risk/estimate inputs, adding little parameter meaning beyond the schema — the baseline 3 for high coverage 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?

States a specific verb and resource ('validate an order against risk limits and estimate fill price and fees') and positions itself in a two-step flow by naming submit_signed_order as the consumer of its output. An agent can distinguish it from submit_signed_order and prepare_position_tpsl without opening any schema.

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?

'Use when you sign transactions yourself' gives a clear selection condition, and the dry_run sentence clarifies the read-only validation mode. It does not name the contrasting alternative (a server-side signing path) or state exclusions, so it stops short of full when/when-not guidance.

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

All TradeForAgents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?