Skip to main content
Glama
Sign In
unity-profiler-mcp

unity-profiler-mcp

by shin0112
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

profiler_summary

Summarize frame times for one Unity Profiler capture, estimating CPU/GPU time from .highlights without the editor and main-thread time from marker exports when available.

Instructions

Frame-time summary of one capture: estimated CPU/GPU frame time from .highlights (no editor needed) and main-thread frame time from the marker export if present.

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": {
      "capture": "<capture>"
    },
    "name": "profiler_summary"
  }
}

Input Schema

NameRequiredDescriptionDefault
folderNoCapture folder. Default: UNITY_PROFILER_CAPTURES or <project>/ProfilerCaptures from the open editor.
captureYesCapture file name (with or without .data) inside the capture folder, or an absolute path.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the CPU/GPU estimate comes from .highlights and needs no open editor, while main-thread timing depends on a marker export being present — i.e., results degrade conditionally. It still omits side effects, cost, and what happens when neither source exists.

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 front-loaded sentence with the primary output named first and the data-source caveats after. Dense but every clause carries information; no filler.

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

Completeness4/5

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

For a two-parameter, no-output-schema tool, the description names the metrics returned and the two data sources, which is enough for an agent to call it correctly. Minor gap: no indication of the returned structure or success/failure conditions when a source is absent.

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 coverage is 100%, so both the capture path/name semantics and the folder default resolution are already documented in the schema. The description adds nothing about parameter formats or folder fallback, 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?

States a concrete verb+resource pair ('Frame-time summary of one capture') with the specific quantities computed (CPU/GPU frame time, main-thread frame time). The 'one capture' scope implicitly separates it from profiler_compare, though no sibling is named explicitly.

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 only implied: an agent can infer this is the quick overview tool versus profiler_top_markers or profiler_export, but the description never says when to pick it over those alternatives or what prerequisites apply. No exclusions or alternatives are named.

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