playcal

Overview Schema Source Related Servers Discussions Admin

playcal_loop

Safely run Unity or Godot editor commands by waiting for a ready editor, executing the action, settling again, and returning a single digest with verification and the first real error.

Instructions

run a Unity Editor command safely: wait until ready, run, wait again, one digest

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_loop"
  }
}

Input Schema

Name	Required	Description	Default
`diff`	No	run --verify before the write too and report only what changed
`name`	No	Editor command for `run` (see `unity command`)
`action`	Yes	settle: wait for a ready Editor. run: settle, run, settle
`engine`	No	godot: settle loads every script headless and reports parse errors as compile_error (default unity)	unity
`expect`	No	check on the --verify read (or the command result). PATH=VALUE, PATH!=VALUE, PATH~TEXT, or bare PATH (exists). * matches any list item: objects.*.name=Probe. Repeatable
`params`	No	passed to the command unchanged; put them after --, e.g. run save_scene -- --name x
`verify`	No	read command run after the write, e.g. "get_hierarchy --depth 1"
`compile`	No	also run `unity recompile` and fail with the compile errors; the Editor says ready even when scripts don't build
`timeout`	No	seconds to wait for a ready Editor (default 120)
`checkpoint`	No	save files with playcal checkpoint before the write; on failure the digest says how to undo
`reload_wait`	No	after the write, wait this long for a reload to start before trusting ready (default: 20 when the command says it needs a recompile, else 0)
`project_path`	No	Unity project folder (needed when several Editors are open), or the Godot project folder

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.1Nov 7, 2026

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description carries the full behavioral burden, and it does disclose the core safety sequence (wait for ready, execute, wait for reload, return a single digest). However it omits important traits that live only in parameter text: that Unity reports ready even when scripts fail to build, that checkpoint enables undo, and what the digest actually contains.

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?

A single short sentence with the safe-loop sequence front-loaded and zero wasted words. It is efficient, though its brevity edges toward under-specification for a 12-parameter tool.

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

Completeness3/5

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

For a 12-parameter tool with no annotations and no output schema, the one-line description does only the minimum. The schema covers parameters well, so the definition is usable, but nothing explains the overall return shape ('one digest') or the multi-engine branching that an agent would want before calling.

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 the schema already explains verify/expect/compile/checkpoint semantics in detail; the baseline of 3 applies. The description adds no syntax, format, or interaction guidance (e.g., how verify combines with expect) beyond what the parameter descriptions provide.

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 states a concrete verb and resource — run a Unity Editor command — and characterizes the safe loop (wait until ready, run, wait again, one digest). It is clear, but it never distinguishes itself from siblings like playcal_observe or playcal_query, and it says 'Unity' even though the action/engine params support Godot, which slightly narrows the apparent scope.

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 safe-loop framing and by the action enum in the schema (settle vs run), but the description never says when to pick this over playcal_observe or playcal_playtest, nor when not to use it. An agent must infer routing from the schema rather than the prose.

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