Skip to main content
Glama

scan_perf

Read-only

Audit a Roblox place for runtime frame-killers such as physics load, CSG unions, precise meshes, shadow lights, particles, and un-yielded loops. Returns a ranked fix list; read-only.

Instructions

Audit the place for runtime frame-killers in one pass (part/physics load, StreamingEnabled, CSG unions, precise meshes, shadow lights, particles, and scripts with un-yielded while true do loops). Returns a ranked fix list. Read-only. For a general census of the place use project_health; for UI that breaks on other screens use scan_responsive.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "scan_perf"
  }
}

Input Schema

NameRequiredDescriptionDefault
placeNoTarget place (PlaceId or project name). Defaults to the bound/sole connected place.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description's 'Read-only' merely restates that. It does add value beyond annotations by disclosing the return contract ('Returns a ranked fix list') and that the whole audit happens 'in one pass', which tells the agent a single invocation covers all checks. It stops short of describing ranking criteria or how findings are classified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with no filler: the audit scope is front-loaded, the return value follows, and the sibling routing comes last. The parenthetical check list is dense but each item is meaningful signal for selection.

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 zero-required-parameter, single-argument read tool with no output schema, the definition supplies the check coverage, the output shape (ranked fix list), the safety profile, and alternative routing. An agent can select and call it correctly with no further information.

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?

Only one optional parameter exists and schema description coverage is 100%, with 'PlaceId or project name' and the default-to-bound-place behavior already documented in the schema. The description adds no further semantics about the `place` argument, so the baseline of 3 applies.

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?

States a specific verb and resource ('Audit the place') and then enumerates exactly what is being audited: part/physics load, StreamingEnabled, CSG unions, precise meshes, shadow lights, particles, and un-yielded `while true do` loops. This is far more specific than the tool name alone and distinguishes it from sibling scanners.

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?

Explicitly routes the agent to alternatives with conditions: 'For a general census of the place use project_health; for UI that breaks on other screens use scan_responsive.' Both when-to-use and when-to-use-something-else are given, so nothing is left to inference.

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