Skip to main content
Glama

Smart-money leaderboard

leaderboard
Read-onlyIdempotent

Rank Polymarket traders from OrcaLayer's Smart Money set (or all wallets).

Returns the top traders by lifetime profit, win rate, volume or trade
count, optionally within one market category. Per wallet:
name, total_pnl (Polymarket's lifetime P&L), market_win_rate with
market_wins / market_losses / resolved_markets, profit_factor (capped at
99.99, with profit_factor_capped), indexed_volume_usd, indexed_trades,
main category, average entry price, open positions and the last trade date.
`total` is how many wallets match the filter. A `notes` block defines each
field.

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": "leaderboard"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoRanking key: "pnl" (lifetime profit, default), "win_rate", "volume" or "trades". "win_rate" orders by the leaderboard's stored win rate, which is computed differently from the market_win_rate shown, so rows can look out of order by that column.pnl
limitNoHow many wallets to return, 1 to 50 (larger values return 50).
filterNo"smart" = OrcaLayer's Smart Money set (default); "all" = every ranked wallet.smart
categoryNoRestrict to wallets mainly trading one category: "Crypto", "Politics", "Sports", "Esports", "Geopolitics", "Economics", "Tech/AI", "Culture" or "Weather" (case-insensitive). Omit for all categories.
under_radarNoTrue = only "Under the radar" wallets: top 10% for form against the price over the last 90 days but not in Smart Money (and not bots). They are outside Smart Money by definition, so this replaces `filter`.
liquidity_providerNoTrue = only Liquidity providers: wallets Polymarket paid $100+ in liquidity rewards over the last 30 days, on 10+ days. Combines with `filter` and `under_radar`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / category / description
      Previous value: -"Restrict to wallets mainly trading one category: \"Crypto\", \"Politics\", \"Sports\", \"Geopolitics\", \"Economics\" or \"Tech/AI\" (case-insensitive). Omit for all categories."New value: +"Restrict to wallets mainly trading one category: \"Crypto\", \"Politics\", \"Sports\", \"Esports\", \"Geopolitics\", \"Economics\", \"Tech/AI\", \"Culture\" or \"Weather\" (case-insensitive). Omit for all categories."
  2. Changed6 schema fields changed
    • addedInput schema / properties / category / description
      Added value: +"Restrict to wallets mainly trading one category: \"Crypto\", \"Politics\", \"Sports\", \"Geopolitics\", \"Economics\" or \"Tech/AI\" (case-insensitive). Omit for all categories."
    • addedInput schema / properties / filter / description
      Added value: +"\"smart\" = OrcaLayer's Smart Money set (default); \"all\" = every ranked wallet."
    • addedInput schema / properties / limit / description
      Added value: +"How many wallets to return, 1 to 50 (larger values return 50)."
    • addedInput schema / properties / liquidity_provider / description
      Added value: +"True = only Liquidity providers: wallets Polymarket paid $100+ in liquidity rewards over the last 30 days, on 10+ days. Combines with `filter` and `under_radar`."
    • addedInput schema / properties / sort / description
      Added value: +"Ranking key: \"pnl\" (lifetime profit, default), \"win_rate\", \"volume\" or \"trades\". \"win_rate\" orders by the leaderboard's stored win rate, which is computed differently from the market_win_rate shown, so rows can look out of order by that column."
    • addedInput schema / properties / under_radar / description
      Added value: +"True = only \"Under the radar\" wallets: top 10% for form against the price over the last 90 days but not in Smart Money (and not bots). They are outside Smart Money by definition, so this replaces `filter`."
  3. Changed1 schema field changed
    • addedInput schema / properties / liquidity_provider
      Added value: +{
      +  "default": false,
      +  "title": "Liquidity Provider",
      +  "type": "boolean"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / under_radar
      Added value: +{
      +  "default": false,
      +  "title": "Under Radar",
      +  "type": "boolean"
      +}
  5. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare this a safe, idempotent, read-only, open-world read, so the description is not burdened with the safety story. It adds genuine behavioral context beyond that: the exact per-wallet payload, the profit_factor cap at 99.99 with a companion flag, and the presence of a `notes` block that defines each field. It does not discuss data freshness, rate limits, or the 50-row ceiling on results.

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

Conciseness4/5

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

Front-loaded with the ranking statement before the field inventory, and every sentence carries information — notably the field list, which substitutes for the absent output schema. The single dense sentence enumerating per-wallet fields is long but earns its place.

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?

With no output schema, the description does the necessary work of enumerating returned fields, explaining that `total` is the match count, and pointing to a `notes` block for field definitions. Given six optional parameters and no required inputs, this is nearly complete; the missing piece is any statement about how results are truncated or paged beyond the limit.

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 description coverage is 100%, so the schema already fully documents all six parameters, including the subtle caveat that win_rate ordering can look out of order. The description contributes only light reinforcement ('optionally within one market category', 'smart set or all wallets') and adds no parameter semantics beyond what the schema provides; baseline 3 applies.

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?

Opens with a specific verb+resource ('Rank Polymarket traders') and immediately scopes the population (OrcaLayer's Smart Money set, or all wallets) plus the ranking keys (profit, win rate, volume, trade count). This is unmistakably a ranked-list tool, which is distinct in kind from the per-wallet and per-market siblings in the catalog.

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

Usage Guidelines3/5

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

Usage context is only implied: the description says the category filter is optional and that `filter` can be smart or all, but it never states when an agent should reach for this tool over wallet_overview or wallet_positions. The richer when-to-use semantics (under_radar supersedes filter, liquidity_provider combines with both) live in the schema, not the description.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.