Skip to main content
Glama

dev_snapshot

Captures the accessibility tree of the Unflick window, listing every visible element with its role, name, state and CSS selector so you can see what is on screen and target it for clicks or text input.

Instructions

The accessibility tree of the unflick window: every visible element with its role, accessible name, state and a CSS selector that feeds straight back into dev_click and dev_text. Reach for this first — it is how you find out what is on screen. Invisible nodes and unnamed wrappers are elided, so what comes back is what a person would see. Needs the GUI running, started with --allow-dev.

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": "dev_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNoHow deep to descend. Default 12.
selectorNoScope to a subtree instead of the whole document.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations present, the description carries the full behavioral burden and does substantial work: it discloses that invisible nodes and unnamed wrappers are elided, states the hard prerequisite of a running GUI launched with --allow-dev, and describes the shape of returned records. It does not mention output size limits, truncation, or latency for large trees, which is the main remaining gap.

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?

Four sentences, front-loaded with the core resource and then the prerequisite, with no filler. The concrete elaboration ('what a person would see') earns its place by explaining the filtering behavior rather than restating the name.

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

Completeness5/5

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

There is no output schema, so the description must describe return values — and it does, listing the four fields per element and the elision rule. Combined with the runtime prerequisite and the downstream tool linkage, an agent has enough to call this correctly on the first attempt.

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 description coverage is 100%, so both parameters (depth with its default of 12, and selector scoping) are already fully documented in structured form. The description adds no parameter-level meaning beyond that — the CSS-selector discussion refers to returned values feeding dev_click/dev_text, not to the selector input. Baseline 3 applies.

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 specific resource and its scope: 'the accessibility tree of the unflick window'. It also enumerates exactly what each returned element carries (role, accessible name, state, CSS selector), which lets an agent distinguish this from siblings like dev_capture or dev_eval 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?

'Reach for this first — it is how you find out what is on screen' gives an explicit priority ordering relative to the other dev_* tools, and the CSS selector's link to dev_click and dev_text clarifies the intended workflow. There is no explicit when-not guidance (e.g. cases where dev_capture is preferable), which keeps it short of a 5.

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