Skip to main content
Glama

click_ui

Click UI controls by accessible name or mark, focusing the window and using the real pointer to avoid screenshots and pixel guessing. Pass a name or mark; optional index resolves ambiguity.

Instructions

Click a control by its accessible NAME, or by a mark number from the last marks capture, in ONE call: the exact coordinate comes from the accessibility tree, the window is focused first, and the click goes through the real pointer (visible cursor), so no screenshot and no pixel estimation is spent. Pass exactly one of name (matched against window's controls, exact accessible name preferred, substring otherwise) or mark. An ambiguous name returns the candidates instead of guessing: disambiguate with index (0-based into that list) or a more specific name. Falls back with a note when the app exposes no tree (use screenshot + zoom + pointer then). then ('desktop'|'screenshot'|'ui'|'none') appends the result; 'ui' shows the click's effect on the controls in the same call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
markNo
nameNo
thenNonone
indexNo
buttonNoleft
doubleNo
windowNo
allow_authNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description fully carries behavioral disclosure. It reveals that the window is focused first, the click uses the real pointer with a visible cursor, coordinates come from the accessibility tree, ambiguous names return candidates instead of guessing, and fallback behavior is explicitly noted.

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?

The description is dense and well-structured, front-loading the core mechanism before detailing options. Every sentence adds necessary guidance; there is no filler or redundancy.

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?

Given the absence of annotations and an 8-parameter schema, the description is largely complete: it covers the main invocation paths, disambiguation, fallback strategy, and post-click behavior. The only notable omissions are the semantics of `button`, `double`, and `allow_auth`, which would be useful for full autonomy.

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 description coverage is 0%, so the description must compensate. It thoroughly explains `name`, `mark`, `index`, `then`, and partially `window`. However, `button`, `double`, and `allow_auth` are not described beyond their schema defaults, leaving some gaps.

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 states a precise verb and resource: click a control by accessible name or mark number through the accessibility tree. It clearly differentiates from sibling tools by emphasizing no screenshot, no pixel estimation, and one-call execution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage rules: pass exactly one of `name` or `mark`, disambiguate ambiguous names with `index` or a more specific name, and fall back to screenshot + zoom + pointer when no accessibility tree exists. It also explains the `then` parameter's options and their effects.

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