Skip to main content
Glama
Sign In
playcal

playcal

by RizgarOzan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

playcal_replay

Records input through the SDK, then replays it as a regression test with fixed frame rate and seed; step frames or compare recordings to catch differences.

Instructions

record input through the SDK, replay it as a regression test with fixed frame rate and seed, step frames

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": {
      "action": "<action>"
    },
    "name": "playcal_replay"
  }
}

Input Schema

NameRequiredDescriptionDefault
fpsNorecord: fixed frame rate the game steps at (default 60)
seedNorecord: UnityEngine.Random seed (default 0)
waitNoseconds to wait for the SDK to finish (default from the frame count)
forceNorecord: overwrite an existing recording
namesNoreplay name (files in <project>/.playcal/replays/), or two files for check
actionYesrecord NAME: record a play session. run NAME: replay it and compare. step: advance a paused Editor. check NAME or check A B: compare offline
framesNorecord: frames to record, 0 = until Play stops (default 600). step: frames to step (default 1)
stop_atNorun: pause the Editor on this replay frame and stay in Play Mode
timeoutNoseconds to wait for a ready Editor (default 120)
toleranceNodecimal marks may differ by this much, absolute; whole numbers must match exactly (default 1e-4)
project_pathNoUnity project folder (default: the open Editor's)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations at all, the description carries the full behavioral burden. It does disclose the important determinism contract (fixed frame rate and seed), which is real value beyond the schema, but it omits prerequisites (open Editor, SDK present), the fact that 'record' can overwrite existing recordings with force, that 'run' stays in Play Mode when stop_at is used, and that calls block on Editor readiness.

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?

It is a single short clause with no filler, and the record-then-replay workflow is front-loaded. Structure is weak, though: it is a comma-spliced fragment that lists three actions without signaling the four-way action enum.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex four-mode tool with 11 parameters, no annotations, and no output schema, so the description must do heavy lifting. It never explains the 'check' mode, never states that recording mutates the project's replay files, and gives no sense of what a run returns on mismatch. The rich schema offsets some of this, but the mode-level behavior is under-documented.

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 description coverage is 100%, so every one of the 11 parameters is already documented in the schema, including per-mode meanings for frames, fps, names, and tolerance. The description adds only the general notion of fixed frame rate and seed, so the baseline 3 applies.

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 description names specific verbs and resources: record input through the SDK, replay it as a regression test, and step frames. That is enough for an agent to know this tool is the record/replay driver, distinguishing it from observation or query siblings. It stops short of a crisp statement of the four modes (the 'check' action is never mentioned), which keeps it from a 5.

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?

Usage is implied by the workflow it sketches (record a session, then replay it as a regression test), but there are no explicit when-to-use/when-not rules and no named alternatives among the many playcal_* siblings. Nothing says which mode to pick for a purely offline comparison or when to prefer a checkpoint/baseline tool instead.

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

Deploy Server

Other Tools