Skip to main content
Glama

Find traders

find_traders
Read-onlyIdempotent

Polymarket traders, filtered and sorted like the page; head lines say what applied and what the defaults hid. copyable: % of checked trades a follower could fill (n=checked); ret_lo: ROIC, profit per copy as % of stake, past window, 80% low end (n=copy10_n); 4★+ needs a 90% low end above 0: copy10_lo90, or book_copy10_lo where rating_basis=book; crowd: % copied within 2 s, upper bound. <=4 KB: the rows that fit.

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": "find_traders"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoname, 0x address, 8-hex or Polymarket URL
noNokeep rows checked clean of these flags, comma list
wkNomin copyable trades a week
catNocategory; children fold (iran → geopolitics)
urlNoa chameleons.markets list URL instead
kindNobot, human or unclear
sortNodefault stars, then ret_shrunk; rated first
limitNorows, default 50; 0 = all
starsNomin stars 1–5, or all; default 3
stateNorating state
fieldsNoall, or a comma list of columns
formatNo
hold_hNomax median hold, hours
offsetNorows to skip
ret_loNoROIC 80% low end above, %
checkedNomin checked trades
active_dNotraded within 7 or 30 days
copyableNomin Copyable %, 0–100
copy10_loNoCopy / $10 low end above, USD (n ≥ 10)
uncrowdedNo1: crowd <= 20%, 0: over

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / sort / description
      Previous value: -"stars (default: then ret_shrunk), ret_lo, copyable, wk or hold_h; rated first"New value: +"default stars, then ret_shrunk; rated first"
    • changedInput schema / properties / state / description
      Previous value: -"rated, too_few or cant_copy"New value: +"rating state"
  2. Changed1 schema field changed
    • changedInput schema / properties / stars / description
      Previous value: -"min stars 1–5, or all; default 2"New value: +"min stars 1–5, or all; default 3"
  3. Changed1 schema field changed
    • changedInput schema / properties / stars / description
      Previous value: -"min stars 1–5, or all; default 3"New value: +"min stars 1–5, or all; default 2"
  4. First observed

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description does add real behavior: head lines report applied filters and hidden defaults, and the '<=4 KB: the rows that fit' clause discloses that results are silently truncated to fit a size budget — important and non-obvious. It does not say how truncation interacts with limit=0 or offset paging, leaving the biggest behavioral risk only half explained.

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

Conciseness3/5

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

Purpose is front-loaded and nothing is padded, which fits a tool with 20 parameters. However the metric glossary is telegraphic to the point of opacity — 'n=copy10_n', 'book_copy10_lo where rating_basis=book', '4★+' — forcing the agent to decode abbreviations before it can reason about results.

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?

For a 20-parameter, no-output-schema tool this is largely complete: it covers defaults, sorting precedence, derived-metric definitions, and the response size cap. Remaining gaps are how truncation and offset interact and what the row shape actually contains, but the glossed column names give a workable picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 95%, so the baseline would be 3. The description exceeds it by defining the derived metrics the schema only names: copyable as percent of checked trades fillable, ret_lo as ROIC 80% low end with its sample size, the 90%-low-end rule behind 4★+, book_copy10_lo as the rating_basis=book variant, and crowd as percent copied within 2s as an upper bound. That is genuine meaning the schema does not carry.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause names the resource (Polymarket traders) and the operation (filtered and sorted), so an agent knows this is a filtered listing tool. It never explicitly contrasts with siblings like get_trader or watch_traders, and 'like the page' assumes familiarity with an external UI, so it stops short of a clean 5.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not guidance and no sibling is named as an alternative, even though get_trader (single trader) is an obvious fork. The only usable signal is implicit: default stars=3 and default sort mean a bare call returns rated traders, which an agent must infer.

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.

Resources