address_transactionsGet list of 20 MOST RECENT transactions made by an address (per page). Only the latest transactions according to the date range are returned.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the burden. It adds useful context about the recency limit ('20 MOST RECENT') and date-range filtering, but it does not disclose pagination mechanics, default behavior for omitted dateRange, or any potential caveats like rate limits or data freshness.
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 concise at two sentences and front-loads the core purpose ('Get list of 20 MOST RECENT transactions'). Every phrase adds meaningful information without 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?
An output schema is provided, so return-value details are not needed. However, for a tool with a single 'request' object parameter and no annotations, the description is thin: it leaves 'page' defaults, chain selection, and spam filtering unexplained. It is adequate for a simple list tool but has gaps an agent would need to resolve from the schema.
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?
Since schema description coverage is 0%, the description must compensate. It mentions 'address' and 'date range' indirectly, but it does not explain the 'page', 'chain', or 'hideSpamToken' parameters. The schema itself contains some property descriptions, but the description fails to cover the request object's structure and leaves the agent dependent on the schema for meaning.
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 uses a specific verb ('Get') and identifies the exact resource ('list of 20 MOST RECENT transactions made by an address'). It also includes scope ('per page') and a distinguishing constraint ('Only the latest transactions according to the date range are returned'), which differentiates it from sibling tools like address_dex_trades or address_counterparties.
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 usage for fetching an address's recent transactions but does not explicitly state when to choose this tool over alternatives or mention exclusions. The statement about date range provides a constraint but no comparative guidance.
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 has a clearly defined purpose, and overlapping tools (e.g., token_flows vs token_recent_flows_summary, nansen_score_top_tokens vs token_discovery_screener) include explicit guidance on when to use them. Even with similar names like prediction_market_trades and prediction_market_address_trades, the descriptions and parameters make the distinction unambiguous.
Most tools follow a domain_prefix_noun pattern (address_, token_, prediction_market_), making them predictable within families. However, outliers like general_search, growth_chain_rank, hyperliquid_leaderboard, and transaction_lookup break the pattern, and some names are long or inconsistently formatted (e.g., smart_traders_and_funds_perp_trades vs smart_traders_and_funds_token_balances).
With 38 tools, the server is far above the typical 3-15 range, making it heavy for agents to navigate. However, Nansen is a broad analytics platform covering wallets, tokens, prediction markets, and smart money activity, so the high count is justifiable as each tool serves a distinct function.
The tool set provides comprehensive coverage across token analysis (ohlcv, trading, holders, flows, PnL, technicals), wallet analysis (portfolio, transactions, counterparties), prediction markets (lookup, orderbook, trades, PnL), and discovery. The only obvious omission is NFT support, but it is explicitly documented as out of scope, so no critical dead ends exist.