Skip to main content
Glama

BitCLI — Crypto Futures & Order Flow

by io.bitcli.mcp
OverviewDiscussionsAdmin

create_alert

BEHAVIOR & SIDE EFFECTS: State-mutating operation. Registers an active in-memory HFT trigger in the C++ engine (<500ns tick evaluation). When triggered, an asynchronous event is pushed via SSE to wake up the agent. Alerts auto-expire after ttl_minutes. Idempotent: repeated calls allocate distinct alert IDs.

WHEN TO USE: Proactively call this tool to eliminate continuous API polling loops when waiting for price levels, breakout corridors, volume spikes, or liquidation cascades.

WHEN NOT TO USE: Do not use to inspect registered alerts (use list_alerts) or cancel alerts (use cancel_alert). Do not use for historical data analysis.

UNIFIED BITCLI SYNTAX EXAMPLES:

  • 'btc 95k' (Price cross)

  • 'sol +3.5% 5m' (Velocity pump detector)

  • '* vol 15m x4' (Global exchange-wide whale volume spike vs SMA20)

  • '* liq z3' (Statistical liquidation cascade anomaly > 3σ)

  • 'eth cvd div 15m' (Order flow CVD divergence)

  • 'btc 90k cd=30m' (With custom 30-minute cooldown)

FAILURE MODES: If command syntax cannot be parsed, returns isError: true with syntax guidance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandYesUnified BitCLI alert command string (e.g. 'btc 95k', '* vol 15m x4 cd=15m').
agent_idNoPersistent agent identifier used to recover alert states across network reconnects.default_agent
ttl_minutesNoSubscription lifetime in minutes (range: 1 to 1440, default: 60). Auto-expires upon expiration.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / agent_id / description
      Previous value: -"Persistent agent or wallet identifier to track and recover alerts across reconnects."New value: +"Persistent agent identifier used to recover alert states across network reconnects."
    • changedInput schema / properties / command / description
      Previous value: -"BitCLI alert command string."New value: +"Unified BitCLI alert command string (e.g. 'btc 95k', '* vol 15m x4 cd=15m')."
    • changedInput schema / properties / ttl_minutes / description
      Previous value: -"Time-To-Live in minutes (1 to 1440). Alert auto-expires after this duration."New value: +"Subscription lifetime in minutes (range: 1 to 1440, default: 60). Auto-expires upon expiration."
  2. Changed5 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "default": "default_agent",
+  "description": "Persistent agent or wallet identifier to track and recover alerts across reconnects.",
+  "type": "string"
+}
    • removedInput schema / properties / coin
      Removed value: -{
-  "description": "Cryptocurrency symbol (e.g., BTC, SOL, ETHUSDT).",
-  "type": "string"
-}
    • addedInput schema / properties / command
      Added value: +{
+  "description": "BitCLI alert command string.",
+  "type": "string"
+}
    • removedInput schema / properties / condition
      Removed value: -{
-  "description": "Pre-compiled HFT anomaly trigger.",
-  "enum": [
-    "volume_spike_x3_5m",
-    "cvd_divergence_15m",
-    "liquidation_z3",
-    "funding_abs_above_001"
-  ],
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "coin",
-  "condition"
-]New value: +[
+  "command"
+]
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: state-mutating, in-memory trigger, asynchronous SSE wake-up, auto-expiry via ttl_minutes, and a parse-failure mode returning isError:true. However, the claim 'Idempotent: repeated calls allocate distinct alert IDs' is internally inconsistent — allocating distinct IDs on repeat is the opposite of idempotent, which could mislead an agent about retry safety.

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 BEHAVIOR & SIDE EFFECTS, then usage routing, then examples — a sensible order with labeled sections. The six syntax examples are individually valuable but make the block longer than strictly necessary; still, each line teaches distinct command grammar.

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 mutating tool with no annotations and no output schema, the description covers side effects, lifetime/expiry, async notification path, and failure behavior. Gaps remain: it does not state whether an alert ID is returned, nor any auth/permission requirements.

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%, so baseline is 3, but the description adds genuine meaning beyond the schema: six concrete BitCLI syntax examples showing how to build `command` (price cross, velocity pump, volume spike, liquidation anomaly, CVD divergence, cooldown modifier) and the ttl_minutes expiry consequence.

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?

States a concrete verb+resource: registers an active in-memory HFT trigger in the C++ engine, with the evaluation latency and notification mechanism named. It explicitly distinguishes itself from sibling tools (list_alerts for inspection, cancel_alert for cancellation), so an agent can route correctly without opening schemas.

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?

Has dedicated WHEN TO USE (replace polling loops for price levels, breakouts, volume spikes, liquidation cascades) and WHEN NOT TO USE sections that name the alternatives (list_alerts, cancel_alert) and exclude historical analysis. Nothing about selection is left to inference.

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

All BitCLI — Crypto Futures & Order Flow toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources