Skip to main content
Glama

Preset Workflow

preset_workflow

Save, list, view, run, or delete reusable multi-step macro presets for GUI automation. Execute recorded interaction sequences atomically across desktop apps.

Instructions

Manages and executes reusable multi-step interaction macro presets.

Actions:

  • 'list' (default if name is None): Lists all saved presets with descriptions.

  • 'run' (default if name is provided): Executes the preset sequence atomically.

  • 'view': Returns the full step sequence and metadata for the specified preset.

  • 'save': Saves or updates a preset sequence to .agents/artifacts/presets/.json.

  • 'delete': Deletes a preset artifact.

Step schema matches batch_actions:

  • {"action": "interact", "target": "b1"}

  • {"action": "type", "target": "e1", "text": "value"}

  • {"action": "click", "x": 100, "y": 200, "button": "left"}

  • {"action": "key", "keys": ["ctrl", "a"]}

  • {"action": "scroll", "dx": 0, "dy": 5}

  • {"action": "hover", "target": "b1"}

  • {"action": "wait", "ms": 50}

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": "preset_workflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
pidNo
nameNo
stepsNo
actionNorun
target_appNo
descriptionNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4/5.0
Behavior4/5

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

With annotations already declaring readOnly=false, destructive=false and idempotent=false, the description still adds real value: 'run' is executed atomically, and 'save' persists to .agents/artifacts/presets/<name>.json, disclosing the storage mechanism and that save acts as an upsert. Gaps remain around what 'atomic' means on failure (rollback or partial application) and what 'delete' removes irrecoverably, which is notable given destructiveHint=false.

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?

The purpose leads, followed by a scannable action list and then step examples that directly compensate for the undocumented nested 'steps' array, so nearly every line earns its place. The step bullets could arguably be trimmed to two or three examples, but they carry information found nowhere in the schema.

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?

Output schema exists, so return format needs no explanation, but for a six-parameter, five-action tool the description leaves real holes: 'pid' and 'target_app' semantics, the relationship between a preset's recorded targets and target_app at run time, and failure behavior for atomic execution. It is adequate to invoke the tool in common cases but not complete for the fully parameterized surface.

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 0%, so the description must carry the full burden; it does document the action enum, the name-based routing for list vs run, the steps structure (via concrete examples matching batch_actions), and implicitly the description field. However, 'pid' and 'target_app' appear nowhere in the description, leaving two of six parameters completely undefined despite the description adding good detail on the other four.

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 — 'Manages and executes reusable multi-step interaction macro presets' — and immediately enumerates the five operations (list, run, view, save, delete), which lets an agent tell it apart from the atomic-action siblings like batch_actions, click, or type_text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Per-action defaults are given explicitly ('list' when name is None, 'run' when name is provided), and each action's purpose is stated, which gives clear context for selection. What is missing is an explicit when-not or a direct comparison telling the agent why to prefer a saved preset over calling batch_actions directly, even though batch_actions is named as the schema twin.

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