qa-mcp-server

Overview Schema Source Related Servers Discussions Admin

tap

Clicks at screen coordinates or on an element found by text, resource ID, or content description, using a fresh UI dump to resolve and target its center.

Instructions

Tap at (x, y), or on the element found by ONE selector (text, resource_id or content_desc), resolved through a fresh UI dump and tapped at its center.

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": "tap"
  }
}

Input Schema

Name	Required	Description	Default
`x`	No
`y`	No
`text`	No	Selector: visible text
`index`	No	Which match to tap
`match`	No		exact
`serial`	No
`resource_id`	No	Selector: resource-id, full or short ('save_button')
`content_desc`	No	Selector: content description

Output Schema

Name	Required	Description	Default
`x`	Yes
`y`	Yes
`serial`	Yes
`dry_run`	Yes
`matched`	No
`match_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 13, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Beyond the annotations (readOnly false, destructive false, openWorld false), the description discloses that element resolution happens against a fresh UI dump and that the tap lands at the element's center – real behavioral context an agent could not derive from the schema. It leaves out failure behavior when nothing matches, but with annotations already covering the safety profile this is a solid addition.

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?

A single front-loaded sentence that states the primary mode first and the selector mode second, with zero filler. Every clause carries information: the coordinate form, the selector set, the exclusivity constraint, and the resolution/tap-point mechanism.

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?

Eight parameters and no required fields make this a forgiving but underspecified call, and the description covers the core decision (coordinates vs one selector). With an output schema present, return values need no explanation. The main residual gap is the unstated pairing requirement for x/y and what happens on a no-match.

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 50%, and the schema already documents text, resource_id, content_desc, index, and serial. The description adds the important mutual-exclusion rule among the three selector parameters, but says nothing about x/y needing to be supplied together, how `match` (exact/contains) pairs with `text`, or when `serial` is required. Baseline 3 fits this partial compensation.

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 specific verb and target plus a clear two-mode model: absolute coordinates (x, y) or a single-element selector resolved to its center. It also explains the resolution mechanism (fresh UI dump). It stops short of contrasting itself with siblings such as press_key or input_text, so an agent must infer which input tool to reach for.

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?

"ONE selector (text, resource_id or content_desc)" is a useful mutual-exclusion constraint that tells the agent not to combine selectors. However, there is no guidance on when to prefer coordinates over selectors, what to do when a selector is ambiguous, or when a sibling tool (press_key, input_text) is the better call.

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

Deploy Server

tap