Swipium

Overview Schema Source Related Servers Discussions Admin

Inspect one element

qa_inspect

Read-only

Inspect a single UI element by @eN reference to retrieve its class, ID, text, bounds, and flags from the last snapshot, helping diagnose mobile app UI issues.

Instructions

Inspect one element: full attributes (class, ids, text, bounds, flags) of an @eN ref from the last qa_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": {
      "sessionId": "<sessionId>",
      "ref": "<ref>"
    },
    "name": "qa_inspect"
  }
}

Input Schema

Name	Required	Description	Default
`ref`	Yes	e.g. "@e3"
`sessionId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false). The description adds genuinely new behavior: the ref must come from the most recent snapshot, which warns the agent that refs can go stale. It does not state what happens when a ref is invalid or missing, which keeps it short of full disclosure.

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?

One sentence, front-loaded with the core purpose and the returned payload, followed by the source constraint on the ref. No redundant or filler wording.

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 must carry the return shape, and it enumerates class, ids, text, bounds, and flags. For a simple two-parameter read tool that is nearly complete; only stale/invalid ref behavior and the sessionId meaning are unaccounted for.

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%: ref has only an 'e.g. "@e3"' hint and sessionId has nothing. The description compensates for ref by explaining it comes from the last snapshot, but sessionId remains undocumented in both places, so the compensation is incomplete.

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?

A specific verb (inspect) plus a single, well-bounded resource (one element) with the returned attribute set enumerated. Naming the @eN ref and tying it to qa_snapshot separates it from the snapshot tool that generates those refs.

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?

The phrase 'from the last qa_snapshot' states the prerequisite: a snapshot must exist and its refs are the input. It implies use-after-snapshot for single-element detail work, but does not explicitly name an alternative or the case where the agent should take a fresh snapshot instead.

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