[$0.02 USDC per call via x402] Top DeFi yield opportunities: highest-APY pools filtered by chain and minimum TVL, with project, symbol, APY breakdown and stablecoin flag. Data from DefiLlama.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | No | Chain name, e.g. Base, Ethereum, Solana, Arbitrum (default Base) | |
| limit | No | Max pools to return (default 10, max 50) | |
| min_tvl | No | Minimum pool TVL in USD (default 1000000) | |
| stable_only | No | true = only stablecoin pools |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses the pricing ($0.02 USDC via x402) which is a notable behavioral trait, the data source (DefiLlama), and the fact that it returns filtered APY rankings. The description adds useful context beyond what a bare schema would provide, though it doesn't describe return format specifics.
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, dense sentence that packs in the pricing, purpose, filtering dimensions, output fields, and data source. Every phrase earns its place with zero filler or 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?
The description reasonably covers the tool's purpose and filtering capabilities. With 100% schema coverage and no output schema requirement, the description sufficiently covers what the agent needs. Could add where sorted results land (e.g., pagination behavior) but for a filter-and-list tool with well-documented params, this is largely 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?
Schema coverage is 100%, so parameters are already well documented with descriptions (chain default, limit range, min_tvl default, stable_only value). The description adds context about what 'stable_only' filters for (stablecoin pools) in the output, but the schema already covers the parameter semantics well. Baseline 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 states 'Top DeFi yield opportunities' with a specific verb and resource. It specifies the output details (project, symbol, APY breakdown, stablecoin flag) and data source (DefiLlama), distinguishing it well from the financial-ish siblings like fear_greed, price, gas, etc.
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 explains the filtering dimensions (chain, minimum TVL) and what data is returned. It doesn't explicitly name sibling alternatives or state when NOT to use this tool, but the filtering criteria and data source give clear context for when to invoke it.
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 distinct by domain (market data, safety, DEX trading, yield, gas), but there is meaningful overlap: token_risk, token_score, and screener all deal with token safety/rug-pull concerns, and screener partially overlaps with trending and token_pairs for discovery. An agent picking between token_risk and token_score could be confused despite the price difference, and screener's safety screening overlaps with both.
All names follow a consistent lowercase noun pattern (fear_greed, gas, ohlc, price, yields, token_pairs, market_summary, etc.), with concise single-word or snake_case single concepts. No verb prefixes, no mixing of conventions, no camelCase. Highly predictable across the whole set.
11 tools for a crypto data API is well-scoped, covering market prices, candles, trending, DEX pairs, token safety, yields, and sentiment. Each tool earns its place with a distinct job, and the count aligns with the breadth of a comprehensive market-data service without becoming bloated.
The surface covers core market data (prices, OHLC, trending, fear/greed), DEX trading (token_pairs, screener), safety (token_risk, token_score), yields, and gas. Minor gaps include no historical yield data, no portfolio/balance tool, and no direct order/trade execution, but for a data-and-safety API the coverage is thorough with no obvious dead ends.
