Skip to main content
Glama

android_navigate_to_node

Locate and navigate to specific UI elements within Android applications. Use symbolic A* pathfinding across the device's spatial graph, replacing slow VLM processes.

Instructions

Layer 3 Persistent A* Symbolic UI Router. Computes the shortest path across known screens in the Spatial Graph and executes taps/swipes via live Shadow DOM feedback without intermediate LLM calls.

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": "android_navigate_to_node"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetNoTarget UI text, resource-id, package name, or screen title (e.g. 'Night Light', 'Display and touch').
confirmedNoSet to true ONLY after explicit human confirmation in chat to execute hazardous/irreversible steps (payment, purchase, delete). Default: false.
max_stepsNoMaximum navigation hops allowed (1-30). Default: 12.
target_hashNoOptional exact target layout hash in 0x... hex or decimal format.
auto_exploreNoWhen true and no known graph route exists (no_route / target_not_found), automatically fall back to live Shadow DOM explore-and-click with bounded scrolling and DAG edge recording. Default: false.
device_serialNoOptional ADB device serial. Defaults to the first connected device.
step_timeout_msNoPer-step Shadow DOM settlement timeout in ms (250-10000). Default: 2000.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
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. It does disclose meaningful behavior beyond the name: autonomous tap/swipe execution with no intermediate LLM checkpoints, driven by live Shadow DOM feedback, which tells an agent this tool acts on the device without asking again. It does not disclose what happens on partial failure, whether actions are reversible, or how hazardous steps are gated (that detail lives only in the 'confirmed' schema field).

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?

Two sentences with no filler, and the core action is stated before the mechanism. The opening 'Layer 3 Persistent A* Symbolic UI Router' is internal taxonomy that costs reading effort without helping tool selection, which keeps it below a 5.

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 7-parameter, annotation-free, output-schema-free routing tool, the definition explains the mechanism but not the outcome contract: what a successful or failed navigation returns, or how partial progress is reported. Given there is no output schema, that omission leaves a real gap. Coverage of the execution model is adequate, coverage of results and failure modes is not.

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 100%, so the schema already explains target, confirmed, max_steps, target_hash, auto_explore, device_serial, and step_timeout_ms thoroughly. The description mentions no parameters at all, adding nothing beyond the structured fields. Baseline 3 applies when the schema does all the work.

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 concrete verb-plus-resource: it computes a shortest path across known screens and executes taps/swipes to reach a target node. 'Layer 3 Persistent A* Symbolic UI Router' is heavy jargon, but the second clause makes the actual function legible. It implicitly separates itself from exploration-style siblings via 'known screens' and 'without intermediate LLM calls', though it never names an alternative tool.

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?

Usage is only implied: it should be used when a route through known screens exists in the Spatial Graph. The description never states when to prefer it over android_tap_element or android_explore_and_click, nor when it will fail. The fallback condition is only discoverable by reading the auto_explore parameter in the schema, not from the description text.

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