PreFlyte — DeFi Financial Intelligence for AI Agents

get_returns

Query historical DeFi lending returns from the ProfitLens engine.

Returns real, empirically measured after-fee returns — not theoretical
APY projections. Data is computed from on-chain index ratios every 30 min.

Args:
    api_key: Your PreFlyte API key (required).
    chain: Filter by chain — "ethereum" or "arbitrum". Empty = all chains.
    protocol: Filter by protocol — "aave-v3" or "compound-v3". Empty = all.
    asset: Filter by asset symbol — "USDC", "WETH", etc. Empty = all.
    strategy: Filter by strategy — "supply" or "borrow". Empty = both.
    window_days: Return window — 7, 14, 30, or 90 days. Default 7.
    limit: Max results to return. Default 20, max 50.

Returns:
    Dictionary with 'results' array and metadata. Each result includes:
    gross_apy_pct, net_apy_pct, gas_cost_pct, data_completeness_pct,
    chain, protocol, asset, strategy, and more.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "api_key": "<api_key>"
    },
    "name": "get_returns"
  }
}

Input Schema

Name	Required	Description	Default
`asset`	No
`chain`	No
`limit`	No
`api_key`	Yes
`protocol`	No
`strategy`	No
`window_days`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedApr 14, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full transparency burden. It discloses that returns are computed from on-chain index ratios every 30 minutes, that they are after-fee, and it describes the response fields. It does not mention rate limits or permission details beyond the API key, but for a read-only query tool this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The docstring-style format is front-loaded with the purpose, then logically organizes parameters and return fields. Every sentence adds meaningful information with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given that there is no output schema and no annotations, the description provides a remarkably complete invocation guide: parameter constraints, defaults, data freshness, and return field names are all covered. The lack of explicit sibling comparisons is not essential for successful invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has zero descriptions, but the description's Args section fully defines all seven parameters, including defaults, allowed values (e.g., chain choices, window_days options), and examples like 'USDC'. This completely compensates for the missing schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with a specific verb and resource: 'Query historical DeFi lending returns from the ProfitLens engine.' It clearly distinguishes this from real-time siblings by emphasizing empirical, after-fee returns rather than theoretical projections.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool by contrasting 'real, empirically measured after-fee returns' with 'theoretical APY projections,' which helps an agent choose it for historical data needs. It does not explicitly name sibling tools or state when not to use it, so it falls short of a perfect score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All PreFlyte — DeFi Financial Intelligence for AI Agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?