Skip to main content
Glama
Sign In

SimianX AI

by io.github.SimianX-AI
OverviewDiscussionsAdmin

Get autopilot events

get_autopilot_events
Read-onlyIdempotent

The autopilot's event log: analyses, signals, position changes, actions. Without after you get the latest events and a cursor; pass that cursor as after (and wait, up to 25 s) to get only what happens next.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "autopilot_id": "<autopilot_id>"
    },
    "name": "get_autopilot_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoSeconds to wait for something new before answering, 0-25
afterNoCursor from the previous answer
limitNoRows, up to 200 (default 100)
typesNoComma-separated event types, any of: autopilot.started, autopilot.stopped, autopilot.paused_budget, autopilot.config_updated, autopilot.action, analysis.completed, analysis.failed, signal.fired, position.changed, timing_gate.changed
autopilot_idYesAutopilot id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / types / description
      Previous value: -"Comma-separated event types"New value: +"Comma-separated event types, any of: autopilot.started, autopilot.stopped, autopilot.paused_budget, autopilot.config_updated, autopilot.action, analysis.completed, analysis.failed, signal.fired, position.changed, timing_gate.changed"
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint. The description adds genuinely useful behavior beyond that: the cursor handshake and that 'wait' can block up to 25 seconds, which tells the agent this is a long-poll. It still says nothing about ordering, retention, or what happens when no events arrive within the wait window.

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?

Two sentences, front-loaded with the resource and its contents before the polling mechanics. The clipped phrasing ('Without after you get...') is slightly telegraphic but carries no filler.

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?

Five parameters with only autopilot_id required, no output schema, and full schema coverage; the description covers the one non-obvious interaction (cursor plus blocking wait) and indicates the return includes events and a cursor. Minor gaps: no guidance on 'types' filtering or 'limit' tuning, and no statement of what an empty wait response looks like.

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 the baseline is 3; the description goes further by explaining the causal relationship between 'after' and 'wait' (pass the prior cursor, then wait for what comes next), which the schema lists separately without linking. 'limit' and 'types' are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb+resource: the autopilot's event log, enumerated as analyses, signals, position changes, and actions. The possessive scope distinguishes it from get_pulse_events and get_sector_events by implication, though it never names those siblings explicitly.

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?

Gives concrete usage protocols: call without 'after' to seed with the latest events plus a cursor, then pass that cursor as 'after' to fetch only new items. It does not state when to pick this over sibling event tools or when to stop polling, so it falls short of full when/when-not/alternatives guidance.

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

All SimianX AI 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