DeFiLlama DeFi data: TVL rankings, protocol details, chain stats, protocol fees/revenue, yield pools, stablecoin market caps.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | No | Filter by chain name | |
| limit | No | Max results (1-100) | |
| action | Yes | ||
| min_tvl | No | Min TVL filter for yields (default 1000000) | |
| protocol | No | Protocol slug (action=protocol) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does not disclose any behavioral traits such as authentication requirements, rate limits, or side effects. The tool is read-only by nature, but that is not explicitly stated. The description only lists data types, leaving the agent unaware of operational constraints.
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, direct sentence that front-loads the key information (source and data types). It is not verbose and avoids fluff. However, it is somewhat list-like and could be structured to better separate actions, but overall it is appropriately concise.
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 tool has 6 distinct actions and 5 parameters, yet no output schema exists. The description does not hint at what each action returns (e.g., arrays of objects, numerical values). Without output schema, the agent needs more context about return formats. The brief list of data categories is insufficient for a multifunction DeFi data tool.
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 80%, meaning most parameters have descriptions in the schema. The tool description adds little beyond listing the broad categories; it does not explain how each action parameter affects the output or what the 'min_tvl' filter does in proportion to 'yields.' The schema already covers parameter basics, so the description provides marginal semantic enrichment.
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 lists the data categories (TVL rankings, protocol details, chain stats, fees/revenue, yield pools, stablecoins) and names the source (DeFiLlama). It distinguishes this tool from sibling tools like crypto_market by focusing on DeFi analytics. However, it lacks a strong action verb like 'retrieve' or 'query,' so it's slightly less explicit.
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?
No explicit guidance on when to use this tool versus alternatives. The description implies it's for DeFi data from DeFiLlama, but does not mention when not to use it or point to other sibling tools for related but different data. This leaves the agent to infer usage from context alone.
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.
Multiple tools overlap in providing crypto price data (crypto_price, crypto_market, crypto_derivatives, global_assets) and news (news_feed, tradfi_news). While descriptions clarify some differences, agents may struggle to choose between similar tools.
Tool names mix styles: some are simple nouns (backtest, cn_market), others compound nouns with underscores (crypto_derivatives, derivatives_sentiment). No consistent verb_noun pattern, making it harder to infer purpose from name alone.
With 19 tools covering a broad domain (crypto, DeFi, macro), the count feels slightly high but justifiable. However, several tools could be merged to reduce overlap and improve navigability.
The tool set covers a wide range of market intelligence needs: price data, technical analysis, sentiment, macro indicators, news, and DeFi. Minor gaps like on-chain analytics or direct trading are acceptable given the intelligence focus.