fuse_smart_transfer_nftSubmits an ERC-4337 UserOperation transferring an NFT (ERC-721 / ERC-1155) from the configured smart wallet to a recipient.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Recipient address. | |
| tokenId | Yes | NFT token ID (decimal or 0x-prefixed hex string). | |
| nftContractAddress | Yes | ERC-721 / ERC-1155 contract address. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It mentions ERC-4337 UserOperation and smart wallet origin but omits critical details: whether prior approval is needed, gas implications, reversibility, side effects, or return value. This is insufficient for safe invocation.
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 sentence that is front-loaded with the action verb 'Submits', directly stating the purpose. No redundant or extraneous text; every word earns its place.
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 mutation tool with 3 parameters and no output schema, the description is moderately complete. It explains the core operation but lacks details on prerequisites (e.g., approval), return value, and edge cases. Given no annotations, this is a notable gap.
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 coverage is 100% with each parameter described (to, tokenId, nftContractAddress). The description adds the context of smart wallet and UserOperation but does not enhance parameter meaning beyond schema. Baseline 3 applies.
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 clearly specifies the action ('Submits an ERC-4337 UserOperation transferring an NFT'), the asset type (ERC-721/ERC-1155), and the origin ('from the configured smart wallet'). This effectively distinguishes it from siblings like fuse_smart_transfer_token (ERC-20) and fuse_send_native.
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?
The description implies usage for smart wallet NFT transfers but does not explicitly state when to use this tool vs alternatives like fuse_smart_approve_nft (for approvals) or non-smart-account transfer tools. No when-not or alternative guidance is provided.
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 have distinct purposes (e.g., balances, trades, staking, notifications), but there is some overlap, such as multiple trading quote tools and parallel EOA vs. smart wallet operations (e.g., send_erc20 vs smart_transfer_token). Descriptions generally clarify differences, so only minor confusion is possible.
All tools follow a consistent `fuse_<verb>_<noun>` pattern (e.g., `fuse_get_balance`, `fuse_send_native`). The notification sub-group uses `fuse_notification_<verb>_<noun>`, which is internally consistent. No mixed conventions or chaotic naming exist.
With 50 tools, the surface is very large and likely overwhelming for agents. Many tools could be combined (e.g., price history and change tools, or multiple notification CRUD tools). The count is excessive for the server's scope, reducing coherence.
The tool set covers a wide range of Fuse operations: token info, balances, staking, trading, ERC-4337 smart wallets, notifications, and contract interaction. The `fuse_explorer_query` tool provides a catch-all for additional explorer endpoints, filling most gaps. Minor missing explicit tools (e.g., block details) are mitigable.