Swipium

Overview Schema Source Related Servers Discussions Admin

Clear an overlay

qa_clear_overlay

Clear mobile screen obstructions such as keyboards, LogBox, permission dialogs, and toasts, then report what was cleared and what remains; optionally verify whether a target element is still blocked.

Instructions

Clear what blocks the screen (keyboard, LogBox, permission dialog, toast); strategy "auto" handles the topmost. targetRef checks whether that element is still obstructed. Returns what was cleared and what remains.

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": {
      "sessionId": "<sessionId>"
    },
    "name": "qa_clear_overlay"
  }
}

Input Schema

Name	Required	Description
`strategy`	No	default "auto"
`sessionId`	Yes
`targetRef`	No	@eN to check obstruction before/after

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare the mutation is non-readonly but non-destructive and non-idempotent. The description adds real value by explaining that 'auto' only handles the topmost blocker and that the return value reports what was cleared and what remains — which explains the non-idempotent behavior. It still omits failure modes (nothing to clear) and permission requirements.

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?

Three compact sentences: the scope first, then the two parameter behaviors, then the return shape. Every clause carries information; the only mild weakness is that the parameter notes are folded into the purpose sentence rather than separated.

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?

With no output schema, the description correctly covers the return shape ('what was cleared and what remains'), and it explains the scope of a single call. Missing only edge-case behavior — what happens if no blocker exists or if a strategy fails — which matters given the non-idempotent hint.

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 67% and the description compensates usefully: it states the 'auto' default and that targetRef is an @eN reference used to test whether that element is still obstructed. Only sessionId is left purely to the schema, which is the least ambiguous parameter.

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?

States a concrete verb and object — 'Clear what blocks the screen' — and enumerates the blocker classes it handles (keyboard, LogBox, permission dialog, toast). That is far more specific than the name alone, though it never names a sibling (e.g. qa_act) to sharpen the boundary between 'acting' and 'clearing an overlay'.

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 implied by the problem domain: call this when something is blocking the screen, and 'auto' picks the topmost obstacle. There is no explicit when-not guidance, no statement about repeated invocation (non-idempotent per annotations), and no named alternative for cases where clearing is the wrong move.

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