polymarket-paper-trader

Run strategy PK battle

pk_battle

Run two trading strategies from scratch on equal balances using live market data and temporary accounts, then return stats, a PK card, and the winner.

Instructions

Run two strategies from scratch on equal balances and return stats, a PK card and the winner.

Executes the strategy functions against live market data in temporary accounts. Use pk_card to compare accounts that already exist, or backtest to test one strategy on historical data.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name_a`	No	Display name of strategy A on the PK card. Default 'player_a'.	player_a
`name_b`	No	Display name of strategy B on the PK card. Default 'player_b'.	player_b
`balance`	No	Starting USD for each strategy. Default 10000.
`strategy_a`	Yes	Dotted Python path of strategy A, e.g. 'examples.momentum.run'; only 'examples.' modules are allowed.
`strategy_b`	Yes	Dotted Python path of strategy B, e.g. 'examples.contrarian.run'; only 'examples.' modules are allowed.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.4.13Oct 16, 2026

addedInput schema / properties / balance / description

Added value: +"Starting USD for each strategy. Default 10000."

addedInput schema / properties / name_a / description

Added value: +"Display name of strategy A on the PK card. Default 'player_a'."

addedInput schema / properties / name_b / description

Added value: +"Display name of strategy B on the PK card. Default 'player_b'."

addedInput schema / properties / strategy_a / description

Added value: +"Dotted Python path of strategy A, e.g. 'examples.momentum.run'; only 'examples.' modules are allowed."

addedInput schema / properties / strategy_b / description

Added value: +"Dotted Python path of strategy B, e.g. 'examples.contrarian.run'; only 'examples.' modules are allowed."

First observedv0.4.1Sep 26, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations declare openWorldHint=true and destructiveHint=false, so the agent already knows this touches live external data non-destructively. The description adds valuable context the annotations do not: execution happens on live market data, in temporary accounts, with equal starting balances. It stops short of noting runtime/cost, so not quite a 5.

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 core action in the first sentence, then sibling routing. Three sentences with no filler, though the line break mid-sentence makes it marginally less tight.

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?

Output schema exists, so return values need no elaboration, yet the description still names them. For a live-execution tool the description covers scope, accounts used, and the alternative tools, leaving only performance/cost characteristics unstated.

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 coverage is 100%, so all five parameters are already documented, including the 'examples.'-only path restriction. The description adds only the implicit 'equal balances' framing, so the schema does the heavy lifting and 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?

Specific verb+resource: 'Run two strategies from scratch on equal balances and return stats, a PK card and the winner.' It clearly distinguishes this head-to-head live run from pk_card and backtest by naming both siblings.

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

Usage Guidelines5/5

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

Explicitly routes the agent: 'Use pk_card to compare accounts that already exist, or backtest to test one strategy on historical data.' The when-to-use and when-to-use-something-else conditions are both stated.

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