Skip to main content
Glama

wallet-tracker

by xyz.cabalspy
OverviewDiscussionsAdmin

get_recent_trades

Read-only
The live feed: what tracked wallets are buying and selling right now, across
every token or filtered to one. Use for "what are KOLs buying at the moment".

blockchain: solana, bnb, base, eth or rh
wallet_type: kol, smart or whale (default kol)
minutes: only trades from the last N minutes, at most 60. Leave at 0 for the
         most recent trades regardless of age.
mint: restrict to one token
limit: how many trades (default 25)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mintNoRestrict the result to a single token. Leave empty for all tokens.
limitNoHow many entries to return. Keep it small: large results are trimmed to fit the context window anyway.
minutesNoOnly trades from the last N minutes, at most 60. Leave at 0 for the most recent trades regardless of age.
blockchainYesBlockchain. One of: solana, bnb, base, eth, rh. solana has kol, smart and whale wallets; bnb, base and rh have kol and smart; eth has kol only. rh is Robinhood Chain, an Ethereum L2.
wallet_typeNoWallet type. kol is a Key Opinion Leader, an influencer whose calls move markets. smart is a wallet selected for its track record. whale is a large holder, Solana only.kol

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedInput schema / properties / blockchain / description
      Added value: +"Blockchain. One of: solana, bnb, base, eth, rh. solana has kol, smart and whale wallets; bnb, base and rh have kol and smart; eth has kol only. rh is Robinhood Chain, an Ethereum L2."
    • addedInput schema / properties / limit / description
      Added value: +"How many entries to return. Keep it small: large results are trimmed to fit the context window anyway."
    • addedInput schema / properties / limit / maximum
      Added value: +200
    • addedInput schema / properties / limit / minimum
      Added value: +1
    • addedInput schema / properties / mint / description
      Added value: +"Restrict the result to a single token. Leave empty for all tokens."
    • addedInput schema / properties / minutes / description
      Added value: +"Only trades from the last N minutes, at most 60. Leave at 0 for the most recent trades regardless of age."
    • addedInput schema / properties / minutes / maximum
      Added value: +60
    • addedInput schema / properties / minutes / minimum
      Added value: +0
    • addedInput schema / properties / wallet_type / description
      Added value: +"Wallet type. kol is a Key Opinion Leader, an influencer whose calls move markets. smart is a wallet selected for its track record. whale is a large holder, Solana only."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "get_recent_tradesDictOutput",
+  "type": "object"
+}
  2. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety and open-world profile is covered. The description's added value is the real-time/freshness characteristic ('what tracked wallets are buying and selling right now') and the 60-minute recency ceiling, but it says nothing about rate limits, latency, or result trimming beyond what the schema already notes.

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?

Purpose is front-loaded in the first sentence and the parameter block is compact and scannable. The per-parameter lines mostly duplicate the schema, which is slightly wasteful but keeps the definition self-contained for an agent reading only the description.

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?

An output schema exists, so return values need no explanation, and annotations cover the read-only/open-world profile. Combined with full schema coverage, the description supplies enough for correct invocation, missing only guidance on sibling selection and behavior under load.

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 every parameter is already documented, including enum-like values for blockchain and wallet_type and the minutes/limit bounds. The description's parameter block largely restates the schema, adding no format, precedence, or interaction detail beyond it.

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?

States a specific verb and resource — a live feed of tracked-wallet buys and sells — and pins the scope with 'right now' and 'across every token or filtered to one'. That real-time framing cleanly separates it from historical siblings like get_wallet_history and get_token_transactions.

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?

Gives a concrete invocation context ('what are KOLs buying at the moment') plus the choice between all-token and single-token scope, which maps to the mint parameter. It stops short of naming a competing sibling or stating when not to use this instead of the history/transaction tools.

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

All wallet-tracker 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