Skip to main content
Glama

Central Command

by co.supabase.rtcelwjnrbmfmrywacky

Agent Strategy Console

cc.agent_strategy
Destructive

Run the Central Command agent console (strategy lifecycle + account actions). Purpose: guide/whoami, create/update strategies, backtest, deploy STOPPED, paper execute, and (explicitly) live orders. Behavior: READ + WRITE. Deploy without execute does NOT move money. Live place_order/close_position/cancel_order require confirm_live=true. Default force_paper=true. Auth: X-Api-Key (linked Connect keys preferred — free). Do not spoof X-Linked-User-Id. Cost: linked Connect keys free; otherwise prepaid / x402 per catalog price for agent-strategy. Rate limit: plan default. Returns: JSON envelope { ok, endpoint, status, data: { ok, guide|whoami|created|deployed|... } }. Guidelines: Start with action=guide then whoami. Prefer paper. Never invent outbound-proxy failures — report real HTTP status/body.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoStrategy id for get/update/deploy/execute/backtest. Optional.
bodyNoFull JSON body merge/override for advanced fields. Optional.
goalNoNatural-language strategy goal / rules. Optional.
titleNoStrategy title when creating/updating. Optional.
actionYesRequired intent. Safe/read: guide, whoami, strategies, get_strategy, portfolio, positions, orders, balance, results, logs, get_backtest. Write (no live money): create_strategy, update_strategy, deploy, pause, backtest, execute with force_paper=true. Destructive live: place_order, close_position, cancel_order — require confirm_live=true. Example: "guide".
settingsNoFor update_strategy: { strategy_config: {max_leverage, max_risk_per_trade_pct, max_concurrent_positions, asset_universe, ...}, capital_config, check_interval_minutes, trading_permissions }. Hot-editable fields work even while running; cold fields (goal, strategy_notes) require pause first. All changes logged.
task_typeNoTask classification for create_strategy. Prefer "paper". Optional.
__x_paymentNoOptional x402 payment proof (same as X-PAYMENT header) when retrying after 402. Optional.
force_paperNoWhen true (recommended default), execute paths stay on paper. Optional.
confirm_liveNoMust be true to place/cancel LIVE exchange orders. Never set unless the human explicitly confirmed. 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

A4.7/5.0
Behavior5/5

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

Adds context beyond annotations: states READ + WRITE behavior, details destructive live actions requiring confirm_live, explains auth (X-Api-Key, linked Connect keys preferred), cost, rate limit, and return format. No contradiction with annotations.

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

Conciseness5/5

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

The description is dense yet well-structured, front-loading the purpose then detailing behaviors and guidelines. Every sentence adds value without redundancy.

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 complexity (10 parameters, nested objects, output schema exists), the description covers purpose, usage, behavioral traits, auth, cost, rate limit, and return format. It references the output envelope, making it complete.

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 100%, but the description adds significant meaning: it categorizes actions (safe/read, write, destructive live) and explains confirm_live and force_paper in depth. It also partially describes the settings object, which is helpful.

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 description clearly states the tool runs the Central Command agent console and lists specific actions (guide/whoami, create/update strategies, backtest, deploy, execute, live orders), distinguishing it from siblings by focusing on strategy lifecycle and account actions.

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?

Provides explicit guidance: start with guide then whoami, prefer paper, never invent outbound-proxy failures, and note that confirm_live is required for destructive live orders. However, it does not explicitly contrast with sibling tools.

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