Token-approval / allowance risk scanner: recent ERC-20 approvals a wallet granted, which are unlimited, and to whom. Send { chain, owner, windows? }. Find risky allowances that could drain your tokens and should be revoked. [x402 paid tool — price $0.05; POST /api/safety/approvals]
| Name | Required | Description | Default |
|---|---|---|---|
| chain | No | Chain, default base | |
| owner | Yes | 0x wallet to scan | |
| windows | No | How many ~9.5k-block windows to scan back, 1-6 (default 3) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description implies a read-only operation ('risk scanner'), but it does not explicitly state whether it is read-only, nor does it discuss rate limits, destructive consequences, or authentication requirements. There is no contradiction with annotations.
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?
The description is concise, front-loaded with the core purpose, and includes extra metadata about pricing and endpoint. Every sentence adds value, though the payment note could be integrated more naturally.
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 the absence of annotations and output schema, the description adequately explains the input and goal but does not describe the output format, pagination, or error handling, leaving some gaps for a scanning tool.
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%, so the schema already documents all parameters. The description redundantly lists parameters in 'Send { chain, owner, windows? }' but adds no new semantic value beyond the schema.
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 defines the tool as a 'Token-approval / allowance risk scanner' that finds recent unlimited ERC-20 approvals. It uses specific verbs like 'scanner' and 'find risky allowances', distinguishing it from sibling tools like safety_simulate or safety_decode.
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 instructs 'Send { chain, owner, windows? }' and states the purpose is to 'Find risky allowances... should be revoked'. This implies when to use, but does not explicitly mention when not to use or list alternatives.
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.
Tools are organized by domain prefix (e.g., 'crypto_', 'rh_', 'snipe_'), which helps distinguish between areas. Within each domain, they serve distinct purposes, though some overlap between domains exists (e.g., price data appears in multiple groups). Overall, an agent can navigate effectively.
All tool names follow a consistent snake_case pattern with a domain prefix and a verb_noun combination (e.g., 'compliance_risk', 'rh_stock', 'snipe_honeypot'). This makes the API predictable and easy to explore.
With 159 tools, the server is extremely large. While the broad scope of web3 and utility functions justifies many tools, the count is significantly above the typical range for a coherent toolkit, potentially overwhelming agents and increasing selection error.
The toolkit covers a wide range of web3 operations: crypto, DeFi, compliance, safety, scheduling, memory, etc. There are no obvious major gaps for its intended purpose, though some niche areas might be missing.