Skip to main content
Glama

Performance Overlay

perf_overlay
Destructive

Draw a recording's CPU or memory track as a small chart with a moving playhead (spikes in red).

Instructions

Draw a recording's CPU or memory track as a small chart with a moving playhead (spikes in red).

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": {
      "input": "<input>"
    },
    "name": "perf_overlay"
  }
}

Input Schema

NameRequiredDescriptionDefault
perfNoIts .perf.jsonl (default: next to input).
inputYesA recording made with perf: true.
widthNoChart width px (default video/4).
cornerNoDefault top_right.
metricNoDefault cpu (the app's) if sampled, else sysCpu.
outputNoOptional output path. Defaults under SCREENCAST_HOME/edits.
overwriteNoAllow replacing an existing file at the output path (default false).

Output Schema

NameRequiredDescriptionDefault
outputPathYesPath of the file written.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.51.1

TDQS

A3.6/5.0
Behavior3/5

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

Beyond the annotations, the description adds useful rendering behavior: a moving playhead and red spikes. It does not explain operational effects such as output-file creation, replacement behavior, or whether the source recording remains unchanged, despite the destructive annotation.

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?

One compact, front-loaded sentence conveys the action, resource, output form, and distinguishing visual details. The parenthetical is informative, and there is no filler or repetition.

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?

Together with the fully described seven-parameter schema and output schema, the description is sufficient for understanding the tool and supplying its required input. It remains thin on operational effects and explicit routing between overlays, which keeps it below the top score.

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% and already documents the input prerequisite, metric choices and fallback, chart sizing, placement, paths, and overwrite behavior. The description's "CPU or memory" broadly echoes the metric parameter without adding meaningful parameter-selection detail, so the high-coverage baseline 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 verb "Draw," the resource "a recording's CPU or memory track," and the result "a small chart" clearly identify a performance-visualization operation. The moving playhead and red spikes further define the output, but the description does not explicitly distinguish this tool from generic or sibling overlay tools.

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?

The wording implies using the tool when CPU or memory performance should be visualized on a recording. It provides no explicit when-not guidance or alternative, and it does not surface the schema's perf:true recording prerequisite as selection guidance.

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