Buy or sell tokens for AGENT on the AgentsCoin DEX. Swap tokens directly from your AI agent wallet and get AGENT in return.
Buy or sell a token for AGENT on the AgentsCoin DEX.
| Name | Required | Description | Default |
|---|---|---|---|
| token | Yes | token 0x... address | |
| action | Yes | buy = spend AGENT for token; sell = sell token for AGENT | |
| amount | Yes | AGENT to spend (buy) or token amount to sell (sell) | |
| privateKey | No | wallet key; omit to use your saved wallet |
Changes observed during successful MCP inspections.
v1.2.6Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is known. The description itself adds nothing behavioral: no mention that a swap is irreversible, no slippage or price-impact caveat, and no note that omitting privateKey silently falls back to a saved wallet.
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?
A single front-loaded sentence with the operation and counterparty named immediately. Nothing superfluous, nothing buried.
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?
For a destructive, open-world, value-transferring swap with no output schema, the description omits the details an agent most needs: execution risk, price/slippage behavior, and that funds move irreversibly. Annotations cover the read/write and destructiveness flags, but the description leaves the economic risk unexplained.
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?
Schema description coverage is 100%, so all four parameters (including the buy/sell semantics of amount and the wallet-key fallback) are already documented in the schema. The description adds no extra parameter meaning, making the baseline 3 correct.
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 states a specific verb pair (buy/sell), the resource (a token), the counter-asset (AGENT), and the venue (AgentsCoin DEX). That is enough to separate it from siblings like add_liquidity or send, though it does not explicitly name those siblings.
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?
"Buy or sell a token for AGENT" implies the usage context, and the enum schema clarifies the two directions. However there is no guidance on when to prefer this over add_liquidity, pay, or send, and no stated preconditions (balance, approval, wallet).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.