Live TVL by blockchain — Ethereum, Base, Solana, Arbitrum, and 50+ chains from DeFiLlama. Rankings, 1D and 7D change, protocol counts, Ethereum dominance, and Base vs ETH TVL comparison for x402 agent context.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| sort_by | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, conveying a safe read operation. The description adds beyond this by identifying DeFiLlama as the data source, indicating 'live' data, and enumerating the metrics returned (e.g., Ethereum dominance, Base vs ETH comparison), which enriches behavioral understanding.
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 a single, front-loaded sentence that begins with the core action ('Live TVL by blockchain') and packs all relevant details—chains, source, metrics—without redundancy or fluff.
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 simple read-only tool with two optional params and no output schema, the description lists the key return metrics and data source, giving a solid idea of the output. Minor omissions like default sorting or response format do not detract significantly given the low complexity.
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 description coverage is 0%, so the description must compensate for parameter explanation. It implicitly maps to sort_by through '1D and 7D change' and 'Rankings', but does not explicitly explain the limit parameter. Given only two simple optional parameters, the partial compensation is adequate but not complete.
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 the tool provides live TVL by blockchain, lists specific chains (Ethereum, Base, Solana, Arbitrum, 50+), and details metrics like rankings, 1D/7D change, protocol counts, and dominance. This differentiates it from sibling benchmark tools such as gas, yield, or correlation benchmarks.
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 implies use for obtaining TVL comparisons and mentions the 'x402 agent context' as a use case, providing clear context. However, it does not explicitly state when to prefer this tool over alternatives or mention exclusions, 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.
Add one secure layer between your agents and this server.
Each tool targets a distinct benchmark category (e.g., chain TVL, yield, options IV, RWA), with no overlapping purposes. The overview tool is clearly different. Agents can easily distinguish them.
Most tools follow 'get_<descriptor>_benchmark' pattern, but 'get_stratalize_overview' breaks the pattern. The naming is otherwise consistent and descriptive.
With 9 tools covering major DeFi and crypto benchmarks (TVL, yields, gas, options, RWA, etc.), the set is well-scoped and each tool serves a clear purpose.
The tool surface covers a broad range of crypto/DeFi benchmarks. Minor gaps exist (e.g., spot price feeds, exchange data), but the set is sufficient for benchmarking and agent discovery.