Skip to main content
Glama

pilot_act

Act once on a uniquely resolved desktop UI element in a fresh snapshot, then verify the expected postcondition in the same window without retrying the mutation.

Instructions

Resolve one unique target in a fresh complete snapshot, act once, and check a unique postcondition in the same window. Never retries a mutation.

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": {
      "app": "<app>",
      "target": "<target>",
      "action": "<action>",
      "expect": "<expect>"
    },
    "name": "pilot_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYes
textNo
actionYes
expectYes
targetYes
window_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.5/5.0
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 key traits: snapshot freshness and completeness, single-action scope, same-window postcondition check, and no retry on mutation. It omits what happens on failure (ambiguity, missing target, failing postcondition) and whether the window is focus-stealing, which are relevant for a UI mutation tool.

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?

Two short sentences, front-loaded with the core pipeline and followed by the critical no-retry constraint. No filler or repeated schema content.

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 description conveys the tool's execution model well, which is the hard part for a compound act-and-verify tool. But for a six-parameter, nested-object, no-output-schema tool, the absence of any parameter or failure-mode explanation leaves meaningful gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across six parameters including two nested objects, and the description explains almost none of them. 'Target' and 'expect' gain loose meaning (uniqueness, postcondition role), but app, text, window_id, and the action enum values are entirely undocumented in prose.

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 specific compound behavior: resolve one unique target in a fresh snapshot, perform one action, then verify a unique postcondition in the same window. This distinguishes it as an atomic act-and-verify primitive rather than a bare click, though the phrase 'target' stays abstract and no sibling is named for contrast.

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?

'Resolve one unique target' and 'check a unique postcondition' imply preconditions for use (uniqueness required), and 'Never retries a mutation' tells the agent not to expect retry semantics. However, there is no explicit when-to-use versus alternatives such as an observe-only or batch tool, so routing 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.