Skip to main content
Glama

gc_controller_sequence

Run a timed sequence of button presses, releases, stick moves, trigger values, waits, and resets on a GameCube controller port to automate gameplay or input tests; supports optional looping.

Instructions

Run a timed input sequence.

Each step is a dict: {"t": ms, "type": "press"|"release", "button": "A"} {"t": ms, "type": "stick", "stick": "main", "x": 0.0, "y": 1.0} {"t": ms, "type": "trigger", "trigger": "L", "value": 1.0} {"t": ms, "type": "wait"} {"t": ms, "type": "reset"} The sequence runs on a background thread. Use gc_controller_sequence_cancel to stop it.

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": {
      "instance_id": "<instance_id>",
      "port": "<port>",
      "steps": "<steps>"
    },
    "name": "gc_controller_sequence"
  }
}

Input Schema

NameRequiredDescriptionDefault
loopNo
portYes
stepsYes
instance_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It does disclose the key behavioral trait that the sequence runs on a background thread and is therefore asynchronous, and it points to the cancel tool. However it omits what happens on invalid steps, whether the call returns immediately or blocks, and whether concurrent sequences are rejected.

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 the action, then the step grammar as scannable indented examples, then the threading and cancellation note. Every line carries information; the only mild waste is that 't' and the millisecond unit are implied rather than stated in a header.

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?

For a complex, unannotated input-injection tool, the description covers the hard part (the step DSL) and the concurrency behavior. Missing pieces such as 'loop' semantics and the meaning of instance_id/port are minor for an agent that already knows the target instance from prior calls.

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

Parameters5/5

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

With 0% schema coverage and 'steps' typed only as an untyped array of free-form objects, the description is the sole documentation of the payload. It spells out five step shapes with their fields (t, type, button, stick/x/y, trigger/value), which an agent could not infer from the schema at all.

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?

The opening sentence names a specific verb and resource ('Run a timed input sequence'), which clearly separates it from the one-shot siblings like gc_controller_press and gc_controller_set_stick. It does not explicitly state the contrast, but the word 'sequence' plus the background-thread note makes the scope unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description names gc_controller_sequence_cancel as the way to stop a running sequence, which is useful lifecycle guidance. It does not say when to prefer this over issuing individual press/release calls, nor any preconditions such as whether a sequence can be started while another is active.

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