Skip to main content
Glama
Sign In

tech-risk

by io.github.rezearcher
OverviewDiscussionsAdmin

defi_yields

Live DeFi lending/LP yield pools, and every pool is tagged with an entry verdict (SUSTAINABLE | DECAYING | OUTLIER | AVOID) + a 0-100 risk_score right in the list — a go/no-go at the browse stage, not just raw rows. Each row carries project, chain, symbol, pool id, APY breakdown incl. 1d/7d/30d trend + apyBase7d/apyMean30d, IL risk incl. il7d, exposure, reward/underlying tokens, outlier flag, mu/sigma, DefiLlama stability forecast, TVL and a stablecoin flag, from DefiLlama, ranked by TVL (or risk-adjusted APY = apy/sigma). For the deep go/no-go on the one pool you're sizing into, pass its pool id to yield_entry_verdict. Cost: $0.005 USDC per call via x402.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "defi_yields"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoSort order: 'tvl' (default) or 'risk_adjusted' (apy/sigma)
chainNoFilter by chain. Short names like eth, arb, op, avax, matic, sol, bnb resolve to the DefiLlama canonical chain name.
limitNoNumber of results, default 20, max 100
stableNoOnly stablecoin pools
projectNoFilter by protocol — the family name (aave, uniswap, curve) resolves all versions, or an exact DefiLlama slug (aave-v3)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / chain / description
      Previous value: -"Filter by chain name"New value: +"Filter by chain. Short names like eth, arb, op, avax, matic, sol, bnb resolve to the DefiLlama canonical chain name."
    • changedInput schema / properties / project / description
      Previous value: -"Filter by DefiLlama project slug"New value: +"Filter by protocol — the family name (aave, uniswap, curve) resolves all versions, or an exact DefiLlama slug (aave-v3)"
  2. Changed1 schema field changed
    • addedInput schema / properties / sort
      Added value: +{
+  "description": "Sort order: 'tvl' (default) or 'risk_adjusted' (apy/sigma)",
+  "enum": [
+    "tvl",
+    "risk_adjusted"
+  ],
+  "type": "string"
+}
  3. Added

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations supplied, the description must carry the behavioral burden, and it does disclose two material facts: the data source (DefiLlama) and a per-call charge of $0.005 USDC via x402. It says nothing about what happens on payment failure, whether results are cached, rate limits, or pagination depth beyond the limit parameter, which are the practical risks for a paid endpoint.

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

Conciseness3/5

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

The strongest content is front-loaded in the first sentence, but the second sentence is a long comma-chained enumeration of every row field (APY breakdown, il7d, mu/sigma, stability forecast, TVL) that is dense and hard to scan. It is informative rather than wasteful, yet the field laundry list could be trimmed or grouped without losing meaning.

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

Completeness4/5

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

Because there is no output schema, the description correctly shoulders the return-value burden and does so thoroughly — naming the verdict enum, risk_score scale, and the row fields, plus the sort modes and data provenance. What remains thin is payment/error behavior and result pagination, which matters for a paid, list-returning endpoint.

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

Parameters3/5

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

Schema coverage is 100%, so all five parameters are already documented, and the baseline is 3. The description reinforces the sort semantics ('risk-adjusted APY = apy/sigma') and confirms short chain names resolve to DefiLlama canonical names only implicitly through the chain parameter's own description, adding little new meaning. It also refers to passing a 'pool id' that is not a parameter of this tool.

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

Purpose4/5

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

The description opens with a specific resource — live DeFi lending/LP yield pools — and adds the distinguishing feature that every row carries a verdict tag and risk_score, so an agent knows this is a browsing/ranking tool rather than a raw data dump. It also separates itself from yield_entry_verdict by framing that sibling as the deep single-pool check. It never mentions the sibling defi_yields_preview, so the paid-vs-free distinction is left implicit.

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?

Guidance is explicit at the routing point: 'For the deep go/no-go on the one pool you're sizing into, pass its pool id to yield_entry_verdict,' which tells the agent exactly when to leave this tool. The cost line ($0.005 USDC per call via x402) also implies the preview sibling should be used first, but that handoff is never stated outright and no when-not-use conditions are spelled out.

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

All tech-risk toolsInspect
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