Skip to main content
Glama

Navigate system or application

app_navigate

Use this when the task calls for a registered app destination or native system settings panel when one safe route can replace multiple clicks; call app_catalog first and verify the opened UI with ui_snapshot.

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": {
      "destination": "<destination>",
      "device": "<device>"
    },
    "name": "app_navigate"
  }
}

Input Schema

NameRequiredDescriptionDefault
appNoApplication id or alias from app_catalog; use system for OS menus and settings.
pidNoOptional exact native application PID, used only for inspect=true to select one of several windows.
stepNoExecute exactly one allowlisted step inside a guided app. For set_search_query also provide query. No arbitrary clicks, sends or submissions.
queryNoOnly with step=set_search_query: 1–256 single-line characters to enter into an exact verified search field. Never presses Enter; omitted from result.
deviceYesReMCP device id returned by list_devices. Required for every device operation.
verifyNoFor application launch only, verify the presence of a real native Accessibility window; opt-in because a busy desktop may require up to 20 seconds. Does not verify foreground focus.
dry_runNoReturn the resolved navigation plan without changing the desktop.
inspectNoFor guided workflows only: read-only inspection of the exact native app window or verified-origin browser tab, without executing the task.
target_idNoOptional exact CDP tab ID for disambiguating multiple matching web-service tabs during inspect=true.
window_idNoOptional exact native window ID, used to disambiguate windows for inspection or a safe step.
destinationYesAllowlisted destination id from app_catalog. Use launch for opening registered third-party applications.
verify_timeout_msNoOptional verification timeout in milliseconds; default 20000, clamped to 2000–30000. Used only with verify=true.
inspect_timeout_msNoNative Accessibility inspection timeout, 2000–30000 ms; default 20000.

Output Schema

NameRequiredDescriptionDefault
dataNoArray/scalar payload wrapper used when the natural result is not an object.
textYesConcise human-readable result of the tool call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the mutation and open-world profile is covered structurally. The description adds useful workflow context (catalog lookup before, snapshot verification after) and hints at an allowlisted 'safe route', but says nothing about failure modes, whether the desktop state changes persist, or what happens if verification fails — the schema, not the description, carries dry_run/verify semantics.

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?

A single compact sentence with the trigger condition front-loaded and no filler. The semicolon-chained clauses pack prerequisite and follow-up into one line, which is dense but efficient for an agent parsing it.

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?

An output schema exists and the input schema is fully documented, so return values and parameter meaning need no coverage here. What is missing for a 13-parameter, open-world navigation tool is the alternative-path guidance (launch_app, browser_navigate_url) and any note on what a failed navigation or verification leaves behind.

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% across all 13 parameters, including the enum for step and the constraints on query, verify_timeout_ms and inspect_timeout_ms. The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies — the schema is doing all the work here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource ('registered app destination or native system settings panel') but never states the action as a verb — the reader has to infer 'navigate/open' from the title. It does partially differentiate itself by positioning app_catalog as a prerequisite and ui_snapshot as the verifier, but the core operation remains implied rather than declared.

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?

It gives a clear triggering condition ('when one safe route can replace multiple clicks') plus an explicit prerequisite sequence: call app_catalog first, then verify the opened UI with ui_snapshot. It stops short of exclusions — nothing says when to prefer launch_app or browser_navigate_url instead, which matters given both appear among the siblings.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources