Skip to main content
Glama

Batch Actions

batch_actions

Runs a sequence of consecutive UI interactions with fail-fast reporting, enabling multi-step desktop automation in a single call.

Instructions

Executes a sequence of consecutive UI interactions with fail-fast reporting.

Supported step schemas:

  • {"action": "interact"|"click"|"double_click"|"right_click", "target": "b1"}

  • {"action": "type"|"set_value"|"clear", "target": "e1", "text": "hello"}

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

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

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

  • {"action": "wait", "ms": 200}

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": {
      "actions": "<actions>"
    },
    "name": "batch_actions"
  }
}

Input Schema

NameRequiredDescriptionDefault
pidNo
actionsYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly=false, destructiveHint=false, and openWorld=false, so the safety profile is covered. The description adds the useful fail-fast reporting behaviour, but it does not say whether already-executed steps persist after a failure, what the failure report contains, or how the optional pid scopes the batched run.

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?

A single front-loaded sentence states the purpose and the fail-fast trait, followed by a compact bulleted list of step schemas. Every line adds information an agent needs to build the actions array; nothing is redundant.

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?

The output schema means return values need not be described, and the step schemas cover the complex actions array well. The tool is still missing the meaning of pid, how targets resolve to UI nodes, and what fail-fast reporting actually returns, which matters for a non-idempotent, non-readOnly batched mutation.

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 coverage is 0%, so the description carries the full burden, and it does so for the actions array by enumerating the six step schemas with their fields and allowed values. The pid parameter is never mentioned, and the target convention (b1, e1 as node references) is only illustrated, not explained, so the coverage is strong but incomplete.

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 first sentence states a specific verb (executes) and resource (a sequence of consecutive UI interactions) and adds the fail-fast reporting trait, which tells an agent this is the batched variant rather than a single interaction. It does not explicitly name the sibling tools (click, type_text) it replaces, so the differentiation is implicit rather than stated.

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 batched framing implies when to use it (multiple consecutive steps instead of repeated single calls), and fail-fast signals that a failing step halts the sequence. However, there is no explicit when-to-use guidance, no stated prerequisites (such as requiring node IDs from inspect_ui_tree), and no named alternative for single interactions.

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