Skip to main content
Glama

desktop_get

Read a desktop UI element's property—text, value, title, bounds, role, or states—using its snapshot ref to inspect accessible content before or after actions.

Instructions

agent-desktop get: Read an element property (text, value, title, bounds, role, states)

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": {
      "ref_id": "<ref_id>"
    },
    "name": "desktop_get"
  }
}

Input Schema

NameRequiredDescriptionDefault
ref_idYesQualified ref from snapshot (@<snapshot_id>:eN)
propertyNoProperty: text (what a person reads: content for text-bearing roles, otherwise the name), value, title, bounds, role, statestext

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.2/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden; the word 'Read' does at least establish that this is a non-mutating lookup. It says nothing about what happens with a stale or invalid ref_id, whether reading triggers any side effect on the UI tree, or what the returned value looks like.

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?

One front-loaded sentence with no wasted words, and the property list is useful at a glance. It reads as a terse fragment rather than a sentence, but nothing is padded.

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?

For a simple two-parameter read tool this is close to adequate, but with no output schema the description should say what a property read returns (a string for text/value/title, presumably structured data for bounds, role, states). The snapshot/ref lifecycle is only implied.

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 the schema already documents both ref_id (qualified ref from a snapshot) and the property list with its default of 'text'. The description's parenthetical merely restates the schema's property enum, adding no format or semantics beyond it, 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?

The description gives a specific verb ('Read') plus the resource ('an element property') and enumerates the retrievable properties (text, value, title, bounds, role, states). It is clear what the tool does, though it never distinguishes itself from adjacent introspection tools like desktop_is or desktop_find.

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

Usage Guidelines2/5

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

There is no guidance on when to call this versus desktop_is, desktop_find, or desktop_check, and no stated prerequisite that a snapshot must exist first. The agent must infer usage entirely from the name and the schema's ref_id note.

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