TronSave

Register Auto Sell

tronsave_register_auto_sell

Create the initial auto-sell configuration for the authenticated user. Returns the persisted autoSettings payload. Side effect: persists automation settings that affect future delegation/sell behavior; not idempotent — calling twice may reset fields. Requires a wallet signature identity. Use for FIRST-TIME setup only; for subsequent edits use tronsave_update_auto_sell_setting, and always read the current state with tronsave_get_user_auto_setting first to avoid overwriting unknown fields. Fails for invalid config combinations, unauthorized sessions, or backend policy restrictions.

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": "tronsave_register_auto_sell"
  }
}

Input Schema

Name	Required	Description
`poolSetting`	No	What the wallet sells automatically: per-resource price floor, duration bounds, minimum amount, reserve, and reclaim scope.
`addOnFeature`	No	Optional extras: voting, auto-stake of idle TRX, suggest-sell hints.
`paymentConfig`	No	Where and how often seller earnings are paid out (address, DAILY/IMMEDIATE, payout window).

Output Schema

Name	Required	Description
`code`	No	GraphQL mutation status code (HTTP-like; `0`/`200` indicates success). Always pair with `success` for routing.
`data`	No	Opaque server-defined payload (tx id, setting id, or status text). Treat as identifier-or-message; rely on `message` for human routing.
`message`	No	Human-readable status text. Populated even on success; localized error messages may appear here on failure.
`success`	No	Whether the mutation succeeded at the backend level. Always check this before reading `data`.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedNov 4, 2026

addedInput schema / properties / addOnFeature / description

Added value: +"Optional extras: voting, auto-stake of idle TRX, suggest-sell hints."

addedInput schema / properties / paymentConfig / description

Added value: +"Where and how often seller earnings are paid out (address, DAILY/IMMEDIATE, payout window)."

addedInput schema / properties / poolSetting / description

Added value: +"What the wallet sells automatically: per-resource price floor, duration bounds, minimum amount, reserve, and reclaim scope."

addedInput schema / properties / poolSetting / properties / bandwidth / description

Added value: +"Auto-sell rules for staked BANDWIDTH; omit to leave BANDWIDTH selling unchanged."

addedInput schema / properties / poolSetting / properties / energy / description

Added value: +"Auto-sell rules for staked ENERGY; omit to leave ENERGY selling unchanged."

Changed14 schema fields changedOct 28, 2026

removedInput schema / properties / paymentConfig / properties / paymentAddress / minLength
```
Removed value: -1
```
addedInput schema / properties / paymentConfig / properties / paymentAddress / pattern
```
Added value: +"^T[1-9A-HJ-NP-Za-km-z]{33}$"
```
changedOutput schema / additionalProperties
```
Previous value: -falseNew value: +{}
```

addedOutput schema / properties / code / anyOf

Added value: +[
+  {
+    "description": "GraphQL mutation status code (HTTP-like; `0`/`200` indicates success). Always pair with `success` for routing.",
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / code / maximum
```
Removed value: -9007199254740991
```
removedOutput schema / properties / code / minimum
```
Removed value: --9007199254740991
```
removedOutput schema / properties / code / type
```
Removed value: -"integer"
```

addedOutput schema / properties / data / anyOf

Added value: +[
+  {
+    "description": "Opaque server-defined payload (tx id, setting id, or status text). Treat as identifier-or-message; rely on `message` for human routing.",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / data / type
```
Removed value: -"string"
```

addedOutput schema / properties / message / anyOf

Added value: +[
+  {
+    "description": "Human-readable status text. Populated even on success; localized error messages may appear here on failure.",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / message / type
```
Removed value: -"string"
```

addedOutput schema / properties / success / anyOf

Added value: +[
+  {
+    "description": "Whether the mutation succeeded at the backend level. Always check this before reading `data`.",
+    "type": "boolean"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / success / type
```
Removed value: -"boolean"
```

removedOutput schema / required

Removed value: -[
-  "code",
-  "success",
-  "message",
-  "data"
-]

First observedJun 3, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the annotations: discloses the concrete consequence of non-idempotency ('calling twice may reset fields'), the persistent side effect on future delegation/sell behavior, the wallet-signature identity requirement, and named failure modes (invalid config combinations, unauthorized sessions, backend policy restrictions). The annotations only supply the boolean hints (readOnlyHint=false, idempotentHint=false); the description explains what those hints mean operationally.

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?

Front-loads purpose, then return value, then side effects, then routing guidance, then failure modes — no wasted sentences. Every clause carries decision-relevant information for an agent choosing between auto-sell tools.

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?

An output schema exists, so return-value explanation is not required, yet the description still names the persisted `autoSettings` payload. For a mutation tool with nested config, the mutation semantics, identity prerequisite, prerequisite read, and failure modes are all covered.

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?

With 3 optional nested parameters at 100% schema description coverage, the schema already documents fields like poolSetting.energy.minPrice, paymentTimeWindow, and reclaim. The description adds no parameter-level meaning, syntax, defaults, or interaction rules, so it sits at the baseline for high-coverage schemas.

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+resource ('Create the initial auto-sell configuration') with explicit scope ('for the authenticated user') and distinguishes it from the sibling it is not ('for subsequent edits use `tronsave_update_auto_sell_setting`'). An agent can select this over update/get siblings 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 Guidelines5/5

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

Explicitly says when to use it ('FIRST-TIME setup only'), when not to ('for subsequent edits use tronsave_update_auto_sell_setting'), and prescribes a prerequisite ('always read the current state with tronsave_get_user_auto_setting first to avoid overwriting unknown fields'). This is the full when/when-not/alternatives pattern.

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

All TronSave 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.