Skip to main content
Glama

Central Command

by co.supabase.rtcelwjnrbmfmrywacky

AI Trade Constructor

cc.trade_builder
Destructive

Call cc.trade_builder — Takes natural language or structured trade ideas, fetches live market context, and generates fully executable order parameters with AI reasoning. Purpose: Takes natural language or structured trade ideas, fetches live market context, and generates fully executable order parameters with AI reasoning. Behavior: mostly READ (plan/validate). WRITE/destructive only when action=execute — that can submit live orders. Prefer action=plan first. Auth: X-Api-Key or x402 payment proof (X-PAYMENT / __x_payment). Anonymous unauthenticated calls receive HTTP 402 with payment accepts. Cost: $0.02 USDC per successful call (x402 Base USDC pay-per-use or prepaid X-Api-Key balance). Linked Connect keys are free. This is billing, not a side effect. Rate limit: 10/min (per API key). Tier: premium. Returns: Complete trade specification: symbol, side, size, leverage, entry type, TP levels, SL level, AI reasoning for each parameter. Guidelines: Prefer paper/simulation paths. For live money require explicit human confirmation (confirm_live / action=execute). Report real HTTP errors; never invent proxy failures. Tags: ai, trade-planning, order-generation, risk-management, automation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ideaYesNatural language trade idea or structured params Required.
risk_pctNoMax risk as % of account Optional.
__x_paymentNoOptional x402 payment proof (same value as X-PAYMENT header). Use when retrying after HTTP 402 if your MCP client cannot set custom headers. Not a business parameter. Optional.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesTrue when the gateway HTTP status is 2xx.
dataNoParsed JSON body from the endpoint (shape varies by slug).
errorNoError message when ok is false.
statusYesUpstream HTTP status from x402-gateway.
billingNoOptional payment / cost metadata when present.
endpointYesCatalog slug that was invoked (e.g. funding-rates).

TDQS

A4.5/5.0
Behavior5/5

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

Beyond annotations (destructiveHint=true, readOnlyHint=false), specifies that most calls are read-only but WRITE occurs only when action=execute. Discloses cost, rate limit, and auth requirements.

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?

Well-structured with sections (purpose, behavior, auth, cost, etc.), but slightly verbose. Front-loads purpose effectively.

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?

Covers return format, error handling (HTTP 402), and guidelines. Output schema existence reduces need for return details. Missing 'action' parameter explanation is a minor gap.

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 baseline is 3. Description explains idea, risk_pct, __x_payment, but the crucial 'action' parameter (plan vs execute) is not in schema and not fully clarified how to invoke 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?

Clearly states it takes natural language or structured trade ideas, fetches market context, and generates executable order parameters. Distinct from siblings like cc.twap_executor (execution) and strategy tools.

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 advises to prefer action=plan first, warns that action=execute submits live orders, and requires human confirmation for live money. Also covers auth, cost, rate limits.

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

All Central Command toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation2/5

Many tools serve overlapping purposes, such as multiple Coinglass data tools (cc.coinglass_data, cc.funding_rates, cc.open_interest, etc.) and multiple AI chat assistants (cc.squirrel_chat, cc.squirrel_chat_v2, cc.openclaw_chat). The distinctions are subtle, likely causing agent misselection.

Naming Consistency5/5

All tool names follow a consistent `cc.<snake_case>` pattern, with verbs like `list_catalog`, `cc.ma_fetch`, and `cc.trade_builder`. No mixing of conventions.

Tool Count3/5

33 tools is on the high side but reasonable for a comprehensive crypto trading platform. However, significant redundancy (e.g., multiple data sources for similar indicators) suggests some could be consolidated, making the surface feel heavier than necessary.

Completeness4/5

The tool set covers most aspects of crypto trading: market data, technical indicators, signals, execution, backtesting, AI analysis, and blockchain RPC. Minor gaps exist (e.g., portfolio management), but the surface is largely complete for the intended domain.

Resources