Skip to main content
Glama

open_url

Open app-specific deep links directly in the app under test—not a browser—to test in-app routing and URL-scheme handling on Android and iOS.

Instructions

Open a deep link in the app under test. The link goes to that app only, never a browser: on Android a link the app has no screen for fails; on iOS only the app's own URL scheme (e.g. myapp://settings) is accepted, and a web or system link is refused.

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": {
      "url": "<url>"
    },
    "name": "open_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesFull URI including scheme, e.g. 'myapp://settings' (max 2048 chars).
session_idNoSession ID to target. Optional: falls back to the MCP-server-held dev_start session, then this project's `vibeview dev --detach` state, if either is available.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations supply only readOnlyHint=false, so the description carries most of the burden and does so well: it discloses that the call is app-scoped, never browser-mediated, and enumerates platform-specific failure modes (Android unmatched link fails, iOS foreign scheme refused). It does not say whether the call blocks until the screen loads or what observable state results, which keeps it from a 5.

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 sentences, zero filler, with the core action front-loaded and the platform caveats following in a tight colon-delimited list. Nothing is repeated from the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no output schema and near-complete schema documentation, the description covers the non-obvious risks — platform-specific URL validity and browser refusal — that the agent cannot learn from structured fields. Minor gap: no statement about post-navigation state (whether the screen is settled when the call returns).

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 100%, so 3 is the floor, but the description genuinely adds meaning: the url must be a full URI using the app's own scheme, and validity is platform-dependent (a scheme that works on iOS may fail on Android if no screen matches). The session_id parameter is left entirely to the schema, which already documents the fallback chain.

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

Purpose5/5

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

Names a specific verb and resource ('Open a deep link') and pins the target ('in the app under test'), immediately ruling out the most likely confusion — that it would hand off to a browser. One sentence is enough for an agent to distinguish it from relaunch_app or dev_reload.

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?

Gives clear context for applicability — the link must target the app's own scheme, and web/system links are refused on iOS while unmatched links fail on Android — which effectively tells the agent when this call will not work. It stops short of naming any sibling alternative (e.g. relaunch_app) for the launch-an-app case, so it is clear context without explicit routing.

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