top_up_gasMove a little USDC from the trading subaccount back to the WALLET when the wallet is at or below $0.55 — just enough to restore the $0.95 gas reserve that deposit/withdraw transactions need. Only the gas reserve, only to the account's own wallet; it cannot send funds anywhere else. Use after a transaction fails for lack of gas.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, the description discloses the exact source, destination, amount, threshold, and safety boundary. This gives a clear picture of the tool's behavior without requiring the agent to infer side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences cover the action, the amount, the constraint, and the recommended context for use. Every sentence contributes concrete information, and the key behavior is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, sparse annotations, and no output schema, the description still explains when to call, what it does, where funds move, how much, and what it cannot do. Nothing necessary for correct invocation is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
This tool has zero parameters, so parameter semantics are largely not applicable. The description helps by making the action fully deterministic and removing any need for a caller to supply additional context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb phrase — 'Move a little USDC from the trading subaccount back to the WALLET' — and clearly identifies the condition and exact reserve amount. It also differentiates itself from siblings like deposit_to_subaccount by making the transfer direction explicit.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides a precise trigger ('when the wallet is at or below $0.55') and an explicit use case ('Use after a transaction fails for lack of gas'). The restriction that it cannot send funds anywhere else makes the limits of use unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly distinct, but there is overlap among the read-heavy account tools: get_balance/get_funding_status/fund virtually duplicate each other, and get_equity/get_portfolio/get_position_risk/get_open_orders/get_positions all converge on equity and open-position data. The detailed descriptions help an agent choose, but several tools have fuzzy boundaries.
The overwhelming majority follow the expected verb_noun convention: get_*, place_*, cancel_*, close_*. Minor deviations such as batch_cancel, get_candles_multi, top_up_gas, and whoami make the pattern not perfectly uniform, but the inconsistency is small.
At 33 tools, the surface is beyond what most agents need and includes several redundant query helpers rather than genuinely distinct operations. A broad exchange can justify a large surface, but get_balance/get_funding_status, get_equity/get_portfolio/get_position_risk, and get_candles/get_candles_multi make the set feel top-heavy.
The core lifecycle is well covered: market discovery, market data, order placement/cancellation, position management, risk, funding transfers, PnL, and account status. Obvious gaps are limited to historical order lookup by order ID, a way to cancel across all markets in one call, and a few optional account-history conveniences.