check_token_safetyFree honeypot / risk screen for an EVM token contract, from the cached GoPlus security dataset. This is the quick screen — the paid analyze_token_security tool runs a live, deeper scan on any contract including ones not in the cache.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | No | Chain the contract is deployed on. | base |
| contract | Yes | Token contract address, 0x-prefixed 40 hex characters. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, but the description adds context about the cached dataset and the limitation that contracts not in the cache are not covered. This clarifies the tool's non-mutating, potentially stale nature beyond the structured 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 two sentences, front-loaded with the core purpose, and immediately provides a relevant alternative. Every word earns its place, with no redundancy.
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 two-parameter read-only tool, the description gives strong context: purpose, data source, and alternative. The only gap is the absence of output format or risk categories, but given the simplicity and the clear scope, it remains mostly complete.
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?
The schema covers 100% of parameters with descriptions for chain and contract. The tool description does not add additional parameter-level meaning, but it does contextualize the contract as 'EVM'. Since the schema already provides full parameter details, the baseline of 3 is appropriate.
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 identifies the tool as a 'free honeypot / risk screen for an EVM token contract' using a cached GoPlus dataset, with a specific verb and resource. It also differentiates from the sibling tool analyze_token_security by positioning it as the quick screen versus a deeper, live scan.
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 explicitly states when to use this tool ('quick screen') and contrasts it with the paid analyze_token_security tool, which runs a live, deeper scan on any contract including those not in the cache. This provides clear guidance on tool selection.
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.
With 40 tools, many share overlapping domains: get_smart_money_flow vs get_smart_money_inflow, scan_launchpads vs get_launchpad_radar, track_whales vs get_hyperliquid_whales, and check_token_safety vs analyze_token_security. The detailed descriptions help, but the boundaries are not always clear, making misselection likely.
The tool names employ a wide variety of verbs (get_, analyze_, scan_, track_, find_, generate_, recommend_, run_, list_, ask_, assess_, detect_) with no consistent pattern. While all use snake_case, the inconsistent verb choices and occasional deviations like forecast_chart prevent predictability.
40 tools is well above the typical 3-15 well-scoped range and exceeds the 25+ threshold for 'too many'. While the broad 'crypto intelligence' purpose justifies some breadth, the sheer number makes the surface unwieldy and suggests a lack of focused scoping.
The tool set covers a wide range of crypto intelligence domains: market analysis, forecasting, whale tracking, yield/arbitrage, security checks, prediction markets, backtesting, and even content generation. Missing operations are minor (e.g., no direct portfolio management), but core analysis and data retrieval workflows are well represented.