Skip to main content
Glama

Top Trade Setups

top_setups

Scan top-volume Pacifica perps and return high-probability setups with entry, direction, leverage, margin, take-profit, stop-loss, measured win rate, and fee-adjusted expected value.

Instructions

Scan top-volume Pacifica perps across three horizons and return the highest-probability setups RIGHT NOW: entry, direction, leverage, margin size, take-profit and stop-loss (as price move AND as % of margin), win rate with sample count, and fee-adjusted expected value.

The three timeframes are NOT fixed, they are whichever ones currently measure the highest expected value, re-selected every 7 days by the re-measurement job. Ask analyze_chart if you need a specific timeframe.

The win rate shown is MEASURED, not a backtest number: it comes from walk-forward validation over ~9 years (Binance history joined to Pacifica), where a prediction is formed using only data available at that moment and then checked against what actually happened. That measurement found the realistic ceiling in this market is about 58%, and that raw backtest values above ~55% do not survive out of sample (a backtest claiming 73% came out at 51% in reality). So expect numbers in the low-to-mid 50s. A setup showing "70%" would be a bug, not an opportunity.

STRICT honesty gates: 30+ occurrences on that exact coin+timeframe, at least 2%p above the base rate, positive EV after fees, and the signal must beat the unconditional baseline for its direction (otherwise it is riding market drift, not skill). Returning ZERO setups is common and correct. Every shown setup is logged for later scoring via review_predictions. Takes 1-2 minutes to scan.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNo
budget_usdNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

The description goes far beyond the annotations by disclosing the measured (not backtested) win rate methodology, strict honesty gates, the possibility of zero setups being correct, the logging behavior via review_predictions, and the 1-2 minute scanning time. This is extensive behavioral disclosure and aligns with the annotations.

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?

The description is long but well-structured: it front-loads the core purpose, then explains the measurement methodology and honesty gates. Every paragraph adds necessary context for a complex tool. It is slightly verbose but justified by the complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, the description covers virtually everything an agent needs to know: exact output fields, timeframe selection, win rate methodology, honesty gates, side effects, and runtime. The only notable omission is the parameter semantics, which is already penalized separately; overall this is near-complete.

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

Parameters1/5

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

The input schema has zero descriptions for its two parameters (top and budget_usd), and the tool description never mentions these parameters or explains how they affect behavior. With 0% schema coverage, the description needed to compensate but did not, leaving the meaning and usage of these parameters entirely ambiguous.

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?

The opening sentence clearly states the tool scans top-volume Pacifica perps and returns the highest-probability setups with a specific list of output fields (entry, direction, leverage, etc.). It also distinguishes from a sibling tool by directing users to analyze_chart for specific timeframe needs.

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?

The description implies this tool is for getting high-probability trading setups right now and explicitly tells users to use analyze_chart if they need a specific timeframe. It does not go as far as providing exhaustive when-not-to-use criteria, but it gives clear context and one direct alternative.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/oceanagent/ocean-agent'

If you have feedback or need assistance with the MCP directory API, please join our Discord server