JW3 MCP Server

Propose trade setup

propose_trade

APPROVAL CARD ONLY — NEVER auto-executed: propose a trade setup for the user to approve in-app (Diary → setups → Send to ticket). Never executes, never moves funds. Needs the trade:propose scope (PAT).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "pair": "<pair>",
      "side": "<side>",
      "entry": "<entry>",
      "stop": "<stop>"
    },
    "name": "propose_trade"
  }
}

Input Schema

Name	Required	Description
`pair`	Yes	e.g. BTC/USDT
`side`	Yes	Side to propose: buy\|sell (long\|short accepted as aliases, normalized to buy\|sell)
`stop`	Yes	Stop-loss price, must be > 0
`asset`	No	Base symbol, e.g. BTC
`entry`	Yes	Entry price, must be > 0
`venue`	No	CEX slug or perps venue
`thesis`	No	One-paragraph rationale
`size_usd`	No	Suggested size in USD, must be > 0
`timeframe`	No	e.g. 4h
`jev_verdict`	No	Optional caller-supplied JEV verdict captured alongside the proposal
`invalidation`	No	Optional invalidation note captured alongside the proposal
`kronos_horizon`	No	Optional Kronos horizon (positive integer)
`kronos_direction`	No	Optional Kronos oracle vote direction
`kronos_captured_at`	No	Optional ISO timestamp of the Kronos vote
`kronos_expected_move_pct`	No	Optional Kronos expected move in percent

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already mark this as non-read-only but non-destructive; the description adds genuinely new context by stating no funds move, no execution occurs, and a trade:propose PAT scope is required. It does not address what happens on repeated calls (idempotentHint is false, so duplicate proposals may accumulate), which is the main undisclosed trait.

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?

A single tightly packed statement with the most consequential constraint (APPROVAL CARD ONLY — NEVER auto-executed) front-loaded in caps, followed by mechanism, side-effect boundary, and auth requirement. No filler sentences.

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 15-parameter mutation-adjacent tool with no output schema, the description covers the safety profile, the approval path, and the auth scope, which are the things an agent most needs. It omits what the call returns (e.g., a proposal identifier or status) and whether duplicate proposals are created on retry.

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% across all 15 parameters, including enum normalization notes for side and validation bounds for prices, so the schema carries parameter meaning fully. The description adds nothing about individual parameters, which is acceptable at full coverage but earns only the baseline.

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 names a specific verb and resource ("propose a trade setup") and immediately pins down the object's nature: an approval card for the user to approve in-app. It explicitly separates itself from execute_trade with "Never executes, never moves funds," so an agent can distinguish it from the execution sibling without opening a 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?

It gives clear context for when this tool applies: a setup the user must approve through Diary → setups → Send to ticket, with an explicit exclusion of auto-execution. It does not route between the other proposal siblings (propose_trade_ideas, propose_bracket, propose_close_all_positions), leaving that choice to inference.

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

All JW3 MCP Server 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.