TradeMemory Protocol

Overview Schema Source Related Servers Discussions Admin

Remember Trade

remember_trade

Save completed trades to outcome-weighted memory and automatically update semantic, procedural, and affective models for future strategy and position sizing.

Instructions

Store a trade into OWM multi-layer memory with automatic updates.

Writes to episodic memory and automatically updates semantic (Bayesian), procedural (running averages + hold time + Kelly), and affective (EWMA confidence/streaks). Also writes to trade_records for backward compatibility.

Input Schema

TableJSON Schema

Name	Required	Description
`pnl`	Yes	Profit/loss in account currency
`pnl_r`	No	P&L as R-multiple (risk units). Improves OWM scoring quality.
`symbol`	Yes	Trading instrument (e.g. "XAUUSD")
`trade_id`	No	Optional custom ID. Auto-generated if omitted.
`direction`	Yes	"long" or "short"
`timestamp`	No	ISO format timestamp. Defaults to now (UTC).
`confidence`	No	Agent confidence level 0-1 (default 0.5)
`exit_price`	Yes	Exit price of the trade
`reflection`	No	Lessons learned from this trade
`entry_price`	Yes	Entry price of the trade
`strategy_name`	Yes	Strategy used (e.g. "VolBreakout")
`context_atr_d1`	No	ATR(14) on D1 in dollars
`context_regime`	No	Market regime (trending_up/trending_down/ranging/volatile)
`exit_timestamp`	No	ISO format exit time. Used to compute hold duration.
`market_context`	Yes	Description of market conditions
`entry_timestamp`	No	ISO format entry time. Used to compute hold duration.
`max_adverse_excursion`	No	Maximum adverse excursion during the trade

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedv0.5.4Aug 2, 2026

addedInput schema / properties / confidence / description

Added value: +"Agent confidence level 0-1 (default 0.5)"

addedInput schema / properties / context_atr_d1 / description
```
Added value: +"ATR(14) on D1 in dollars"
```

addedInput schema / properties / context_regime / description

Added value: +"Market regime (trending_up/trending_down/ranging/volatile)"

addedInput schema / properties / direction / description
```
Added value: +"\"long\" or \"short\""
```
addedInput schema / properties / entry_price / description
```
Added value: +"Entry price of the trade"
```

addedInput schema / properties / entry_timestamp

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "ISO format entry time. Used to compute hold duration."
+}

addedInput schema / properties / exit_price / description
```
Added value: +"Exit price of the trade"
```

addedInput schema / properties / exit_timestamp

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "ISO format exit time. Used to compute hold duration."
+}

addedInput schema / properties / market_context / description
```
Added value: +"Description of market conditions"
```
addedInput schema / properties / max_adverse_excursion / description
```
Added value: +"Maximum adverse excursion during the trade"
```

addedInput schema / properties / pnl / description

Added value: +"Profit/loss in account currency"

addedInput schema / properties / pnl_r / description

Added value: +"P&L as R-multiple (risk units). Improves OWM scoring quality."

addedInput schema / properties / reflection / description
```
Added value: +"Lessons learned from this trade"
```
addedInput schema / properties / strategy_name / description
```
Added value: +"Strategy used (e.g. \"VolBreakout\")"
```

addedInput schema / properties / symbol / description

Added value: +"Trading instrument (e.g. \"XAUUSD\")"

addedInput schema / properties / timestamp / description

Added value: +"ISO format timestamp. Defaults to now (UTC)."

addedInput schema / properties / trade_id / description

Added value: +"Optional custom ID. Auto-generated if omitted."

First observedv0.4.0Mar 12, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations declare non-readonly, non-idempotent, non-destructive, and the description adds substantial detail: which memory layers get written, that semantic updates use Bayesian methods, procedural uses running averages/Kelly, and affective uses EWMA. It also discloses backward-compat write to trade_records. This is real behavioral context beyond what annotations provide.

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?

Four sentences, front-loaded with the main action and then detailing the memory layers. No wasted words; each clause adds information about write targets.

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?

Given the tool's complexity (17 params, multi-layer memory writes) and the presence of an output schema, the description covers the essential write behavior. It omits return-value details but those are in the output schema, which is acceptable.

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%, so all 17 parameters are documented in the schema. The description doesn't mention any specific parameter semantics (e.g., how confidence or pnl_r feed into scoring), so it's baseline 3 for a fully-covered schema.

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?

States a specific verb (store) and resource (trade) and clarifies the target system (OWM multi-layer memory). It doesn't explicitly differentiate from sibling recall_memories or get_trade_reflection, but the write-vs-read distinction is implied by 'Store'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to call this versus alternatives like recall_memories or how often trades should be recorded. The description explains mechanics of what gets updated but never says when an agent should invoke it.

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