Skip to main content
Glama
EL4CTEO

Roblox Studio MCP

Performance and memory

performance
Read-onlyIdempotent

Diagnose why a Roblox place runs heavy: read engine counters, profile script CPU, trace executed lines, break down scene triangles and memory, and find broken asset references.

Instructions

Reads the engine's own counters, and can run the script profiler.

snapshot returns what the Developer Console shows: frame, physics and render times in milliseconds, instance and part counts, draw calls, network rates, and memory broken down by category. Use it to answer 'why is this place heavy' with numbers instead of guesses.

profile runs Studio's script profiler — the Script Performance window — for seconds and reports which scripts consumed CPU. It blocks for that long, so keep it short. It only sees code that actually runs, so start a playtest first; profiling an idle edit session returns nothing.

coverage reports which lines of which scripts actually executed — dead code, untested branches, whether a fix was even reached. Pass enable first, then play, then read the coverage back FROM THE PLAYTEST session, not the editor: instrumenting is per data model, and the playtest is a different one. enable is remembered for the place and re-applied by each new session as it loads. Pass an empty enable array to stop.

What it can and cannot see: instrumentation is fixed when a script is first compiled, so it measures modules required after that point — where most game logic lives — but never a script that starts with the place, which the data model compiles before any plugin exists. Those report 0 lines and are named as unmeasurable rather than counted as dead code.

scene breaks the place down by what it is actually made of: instances by category, triangles and draw calls FOR WHAT THE CAMERA CAN SEE, and the assets holding script, animation and audio memory — each named, so "2.4GB of memory" becomes "this animation is 138KB and these are the Animators using it". It also reports UNPARENTED INSTANCES, which is the closest thing here to a leak detector: objects still alive with nothing holding them in the tree, invisible to find and to tree because they are in neither.

The triangle and draw-call section is the one number here that depends on where the camera is pointing, and it moves enormously: the same place measured 332 triangles looking at empty sky and 29,060 looking at 1,800 parts, seconds apart. So it answers "how heavy is this view", not "how heavy is this place" — point the camera first with viewport op="focus", and compare two views only if both were framed the same way.

audit is a health check rather than a performance one: it finds every reference in the place that points at NOTHING. A Sound whose id was deleted or made private plays silence, a Decal shows nothing, an Animation does nothing — none of them errors, none warns, and the instance looks perfectly healthy because the id is still a string. The only other way to find them is to play the game and notice something missing. It also reports ids left blank, scripts left Disabled, and same-named siblings, which is what makes WaitForChild return the wrong one.

audit fetches the assets to test them, so Studio's Output window will show load errors for the dead ones. That is the engine confirming the finding, not a fault in the tool.

Frame and network figures are only meaningful while something is running. Instance counts and memory are useful in edit mode too.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opNo'snapshot' reads counters now; 'profile' samples running scripts; 'coverage' reports which lines have executed; 'scene' breaks the place down by what it is made of; 'audit' finds broken asset references and other silent faults.snapshot
enableNocoverage only: scripts to start measuring. Remembered for this place and switched on by every session that loads afterwards, so a playtest instruments them before its scripts run. An empty array stops instrumenting.
secondsNoprofile only: how long to sample. The call blocks for this long.
sectionNoscene only: return just one section instead of all six.
studioIdNoTarget Studio; omit for the active one.
frequencyNoprofile only: samples per second. Higher is more precise and costlier.
includePluginsNoprofile only: include Studio plugins in the results. Off by default — an idle Studio is mostly plugin activity, which buries the place's own scripts.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.5
    • changedInput schema / properties / op / description
      Previous value: -"'snapshot' reads counters now; 'profile' samples running scripts; 'coverage' reports which lines have executed; 'scene' breaks the place down by what it is made of."New value: +"'snapshot' reads counters now; 'profile' samples running scripts; 'coverage' reports which lines have executed; 'scene' breaks the place down by what it is made of; 'audit' finds broken asset references and other silent faults."
    • changedInput schema / properties / op / enum
      Previous value: -[
      -  "snapshot",
      -  "profile",
      -  "coverage",
      -  "scene"
      -]New value: +[
      +  "snapshot",
      +  "profile",
      +  "coverage",
      +  "scene",
      +  "audit"
      +]
  2. First observedv0.1.8

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial behavioral context beyond them: `profile` blocks for `seconds`, instrumentation is fixed at compile time and per-data-model, place-starting scripts report 0 lines as unmeasurable, `audit` deliberately surfaces asset load errors in Output, and frame/network figures are only meaningful while running. It even discloses that `enable` is remembered for the place and re-applied by future sessions, a persistent side effect worth flagging.

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 long, but it is organized as op-labeled paragraphs front-loaded with the tool's role, and most sentences carry load-bearing detail. A few clauses (e.g. the restatement of camera-dependence) could be tightened, so it falls just short of fully efficient.

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?

With no output schema, the description carries the return-value burden and does so for every op: snapshot's counters, profile's CPU consumers, coverage's executed lines, scene's categories/triangles/assets/unparented, and audit's dead references. Given the tool's complexity and 7 parameters, nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so the schema already documents each parameter and the baseline is 3. The description nevertheless adds workflow meaning the schema lacks — the enable→play→read-back-from-playtest ordering, the per-data-model instrumentation caveat, and the camera-framing dependency for `scene` triangles — which raises it above baseline.

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?

Names a concrete verb+resource and then differentiates all five ops (`snapshot`, `profile`, `coverage`, `scene`, `audit`) with distinct purposes. It explicitly positions itself against siblings, noting unparented instances are 'invisible to `find` and to `tree`,' so an agent can separate this tool from those without opening a schema.

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?

Gives explicit when/when-not and sequencing for each op: start a playtest before `profile`, pass `enable` first then play then read coverage from the playtest session, point the camera with `viewport op="focus"` before `scene`, and compare views only if framed identically. It also states the condition that selects `audit` over 'play the game and notice something missing.'

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