Skip to main content
Glama
Sign In
agent-bridge

agent-bridge

by avas-app
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

screen.refresh

screen_refresh

Triggers pull-to-refresh on the scrollable holding the target (or the largest visible RefreshControl), then waits for the render so agents can continue with screen.waitFor.

Instructions

Pull to refresh: call the onRefresh of the RefreshControl of the scrollable holding a target (or the largest one with a RefreshControl on screen), then wait for the render. It does not wait for the data: follow with screen.waitFor.

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": "screen_refresh"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNoThe tool's arguments, in order (each any JSON value). Leave out for none.
fullNoReturn a result over 32 KB whole instead of a summary of its size and shape.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.2

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description still discloses the single most important behavioral trap: it does not wait for the data, only for the render. It also documents the implicit target-resolution heuristic, which is non-obvious behavior an agent could not predict from the name. The gap is failure behavior, since nothing says what happens when no RefreshControl is found or whether an error is raised.

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, with the action and default targeting first and the critical 'doesn't wait for data' caveat plus the follow-up call front-loaded directly after. No filler or restated boilerplate.

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, zero-required action tool with no output schema, the definition covers what it does, which element it acts on, and how it fits into a call sequence. It falls short only on error/no-target behavior and on the meaning of the opaque 'args' passthrough.

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%, so both parameters are already documented in the schema, which sets the baseline at 3. The description adds nothing about what 'args' are passed to onRefresh or when to use 'full', so it does not compensate beyond the schema.

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?

The description names a concrete action (triggering RefreshControl.onRefresh on a scrollable) plus the exact target-resolution rule (the scrollable holding the target, or the largest one with a RefreshControl on screen), and it names the follow-up sibling screen.waitFor. An agent can tell what this does and how it differs from a plain wait or scroll without opening a schema.

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 explicit sequencing guidance: this triggers the refresh and waits only for render, so the data is not loaded yet and the caller should follow with screen.waitFor. It also explains the target-selection fallback. What is missing is any when-not-to-use guidance, such as what to do when no RefreshControl exists on screen.

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

Deploy Server

Other Tools