Skip to main content
Glama

remove_liquidity

Remove liquidity from a trading pool on Paloma DEX by specifying chain, token addresses, and liquidity amount to withdraw funds.

Instructions

Remove liquidity from a trading pool using the Trader contract.

Args:
    chain_id: Chain ID (1, 10, 56, 100, 137, 8453, 42161)
    token0_address: Address of first token
    token1_address: Address of second token
    liquidity_amount: Amount of liquidity tokens to remove in wei

Returns:
    JSON string with liquidity removal transaction details.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chain_idYes
token0_addressYes
token1_addressYes
liquidity_amountYes

Implementation Reference

  • The core handler function implementing the remove_liquidity MCP tool. It validates inputs, connects to the chain's Web3, interacts with the Trader contract at the chain-specific address, builds the remove_liquidity transaction call with token0, token1, and amount parameters, estimates gas, signs with private key, sends the transaction, waits for confirmation, and returns detailed JSON results including tx hash, status, explorer link, etc.
    @mcp.tool()
    async def remove_liquidity(ctx: Context, chain_id: str, token0_address: str, token1_address: str, liquidity_amount: str) -> str:
        """Remove liquidity from a trading pool using the Trader contract.
        
        Args:
            chain_id: Chain ID (1, 10, 56, 100, 137, 8453, 42161)
            token0_address: Address of first token
            token1_address: Address of second token
            liquidity_amount: Amount of liquidity tokens to remove in wei
        
        Returns:
            JSON string with liquidity removal transaction details.
        """
        try:
            paloma_ctx = ctx.request_context.lifespan_context
            
            if chain_id not in CHAIN_CONFIGS:
                return f"Error: Unsupported chain ID {chain_id}"
            
            config = CHAIN_CONFIGS[chain_id]
            
            if chain_id not in paloma_ctx.web3_clients:
                return f"Error: Web3 client not available for {config.name}"
            
            trader_address = TRADER_ADDRESSES.get(chain_id)
            if not trader_address:
                return f"Error: Trader contract not configured for {config.name}"
            
            # Validate addresses and amount
            if not Web3.is_address(token0_address):
                return f"Error: Invalid token0 address: {token0_address}"
            
            if not Web3.is_address(token1_address):
                return f"Error: Invalid token1 address: {token1_address}"
            
            try:
                amount_int = int(liquidity_amount)
                if amount_int <= 0:
                    raise ValueError("Amount must be positive")
            except ValueError:
                return f"Error: Invalid liquidity amount: {liquidity_amount}"
            
            web3 = paloma_ctx.web3_clients[chain_id]
            trader_contract = web3.eth.contract(address=trader_address, abi=TRADER_ABI)
            
            # Get gas fee from contract
            try:
                gas_fee = trader_contract.functions.gas_fee().call()
            except Exception as e:
                logger.warning(f"Failed to get gas fee from contract: {e}, using 0")
                gas_fee = 0
            
            # Build transaction
            remove_liquidity_tx_data = trader_contract.functions.remove_liquidity(
                token0_address,
                token1_address,
                amount_int
            ).build_transaction({
                'from': paloma_ctx.address,
                'value': gas_fee,
                'gasPrice': web3.to_wei(config.gas_price_gwei, 'gwei'),
                'nonce': web3.eth.get_transaction_count(paloma_ctx.address)
            })
            
            # Estimate gas with buffer
            try:
                estimated_gas = web3.eth.estimate_gas(remove_liquidity_tx_data)
                buffered_gas = estimated_gas + (estimated_gas // GAS_MULTIPLIER)
                remove_liquidity_tx_data['gas'] = buffered_gas
            except Exception as e:
                logger.warning(f"Gas estimation failed: {e}, using default")
                remove_liquidity_tx_data['gas'] = 400000
            
            # Sign and send transaction
            signed_tx = paloma_ctx.account.sign_transaction(remove_liquidity_tx_data)
            tx_hash = web3.eth.send_raw_transaction(signed_tx.rawTransaction)
            
            # Wait for confirmation
            receipt = web3.eth.wait_for_transaction_receipt(tx_hash)
            
            # Get token symbols for display
            try:
                token0_contract = web3.eth.contract(address=token0_address, abi=ERC20_ABI)
                token1_contract = web3.eth.contract(address=token1_address, abi=ERC20_ABI)
                token0_symbol = token0_contract.functions.symbol().call()
                token1_symbol = token1_contract.functions.symbol().call()
            except:
                token0_symbol = "Unknown"
                token1_symbol = "Unknown"
            
            result = {
                "chain": config.name,
                "chain_id": config.chain_id,
                "trader_contract": trader_address,
                "token0": {
                    "address": token0_address,
                    "symbol": token0_symbol
                },
                "token1": {
                    "address": token1_address,
                    "symbol": token1_symbol
                },
                "liquidity_amount_wei": liquidity_amount,
                "transaction": {
                    "hash": tx_hash.hex(),
                    "status": "success" if receipt.status == 1 else "failed",
                    "gas_used": receipt.gasUsed,
                    "gas_fee_paid": str(gas_fee),
                    "block_number": receipt.blockNumber
                },
                "explorer_url": f"{config.explorer_url}/tx/{tx_hash.hex()}"
            }
            
            return json.dumps(result, indent=2)
            
        except Exception as e:
            logger.error(f"Error removing liquidity: {e}")
            return f"Error removing liquidity: {str(e)}"
  • The ABI schema definition for the remove_liquidity contract function within TRADER_ABI, which defines the exact input parameters (token0 address, token1 address, amount uint256) used by the tool handler to call the Trader contract.
        "name": "remove_liquidity",
        "type": "function",
        "inputs": [
            {"name": "token0", "type": "address"},
            {"name": "token1", "type": "address"},
            {"name": "amount", "type": "uint256"}
        ],
        "outputs": [],
        "stateMutability": "payable"
    },
  • Chain-specific addresses of the Trader contracts that expose the remove_liquidity function, referenced by the handler to target the correct contract on each supported EVM chain.
    TRADER_ADDRESSES = {
        ChainID.ETHEREUM_MAIN: "0x7230EC05eD8c38D5be6f58Ae41e30D1ED6cfDAf1",
        ChainID.ARBITRUM_MAIN: "0x36B8763b3b71685F21512511bB433f4A0f50213E", 
        ChainID.BASE_MAIN: "0xd58Dfd5b39fCe87dD9C434e95428DdB289934179",
        ChainID.BSC_MAIN: "0x8ee509a97279029071AB66Cb0391e8Dc67a137f9",
        ChainID.GNOSIS_MAIN: "0xd58Dfd5b39fCe87dD9C434e95428DdB289934179",
        ChainID.OPTIMISM_MAIN: "0xB6d4AAFfBbceB5e363352179E294326C91d6c127",
        ChainID.POLYGON_MAIN: "0xB6d4AAFfBbceB5e363352179E294326C91d6c127"
    }
  • The full ABI for the Trader contract, including the remove_liquidity function signature, used to create the contract instance in the handler.
    TRADER_ABI = [
        {
            "name": "purchase",
            "type": "function",
            "inputs": [
                {"name": "from_token", "type": "address"},
                {"name": "to_token", "type": "address"},
                {"name": "amount", "type": "uint256"}
            ],
            "outputs": [],
            "stateMutability": "payable"
        },
        {
            "name": "add_liquidity",
            "type": "function",
            "inputs": [
                {"name": "token0", "type": "address"},
                {"name": "token1", "type": "address"},
                {"name": "amount0", "type": "uint256"},
                {"name": "amount1", "type": "uint256"}
            ],
            "outputs": [],
            "stateMutability": "payable"
        },
        {
            "name": "remove_liquidity",
            "type": "function",
            "inputs": [
                {"name": "token0", "type": "address"},
                {"name": "token1", "type": "address"},
                {"name": "amount", "type": "uint256"}
            ],
            "outputs": [],
            "stateMutability": "payable"
        },
        {
            "name": "gas_fee",
            "type": "function",
            "inputs": [],
            "outputs": [{"name": "", "type": "uint256"}],
            "stateMutability": "view"
        }
    ]
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a removal operation (implying mutation/destruction of assets) and mentions it returns transaction details, but doesn't disclose critical behavioral traits: whether this requires specific permissions, gas costs, irreversible nature, confirmation requirements, rate limits, or what happens to the removed tokens. For a financial transaction tool with zero annotation coverage, this is a significant gap.

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?

The description is appropriately sized and well-structured with clear sections (purpose, args, returns). Every sentence earns its place, though the 'Args:' and 'Returns:' labels could be slightly more integrated. It's front-loaded with the core purpose and efficiently documents parameters without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given this is a 4-parameter mutation tool with no annotations and no output schema, the description is moderately complete. It covers the basic operation and parameters well, but lacks critical context about behavioral implications (safety, permissions, consequences) and doesn't describe the return value structure beyond 'JSON string with transaction details'. For a financial operation, more completeness would be expected.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description fully compensates by providing clear parameter semantics beyond the schema. It explains what each parameter represents (chain ID with specific values, token addresses, liquidity amount in wei), adding crucial context that the bare schema titles lack. The only minor gap is not specifying format requirements for addresses beyond 'Address'.

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 clearly states the specific action ('Remove liquidity') and resource ('from a trading pool using the Trader contract'), distinguishing it from siblings like 'add_liquidity' (opposite operation) and other trading tools. It provides a complete verb+resource+method statement that leaves no ambiguity about the tool's function.

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?

The description provides no guidance on when to use this tool versus alternatives. While it's clear this is for removing liquidity, there's no mention of prerequisites (e.g., needing existing liquidity positions), conditions for use, or relationship to other tools like 'check_token_allowance' that might be needed first. The agent must infer usage context from the tool name alone.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/VolumeFi/mcpPADEX'

If you have feedback or need assistance with the MCP directory API, please join our Discord server