ReMCP

Computer Focus

computer_focus

Use this to bring an identified native desktop control into focus before typing or interacting with it. Prefer a current semantic target; focusing alone does not type text or activate a button.

Input Schema

Name	Required	Description
`x`	No	Virtual-desktop X coordinate used by click/scroll coordinate targeting.
`y`	No	Virtual-desktop Y coordinate used by click/scroll coordinate targeting.
`id`	No	Element id returned by ui_snapshot or ui_find. Linux ids are stable per-process accessibility paths and legacy linux:<index> ids remain accepted.
`app`	No	Limit matching to an application/process name substring when available.
`pid`	No	Limit matching to one owning process id when available.
`name`	No	Accessible name/title substring.
`role`	No	Accessible role such as Button, Edit, textbox or AXButton.
`label`	No	Compact numeric label from the most recent ui_snapshot/ui_find; useful for repeated actions without repeating names or coordinates.
`title`	No	Optional browser page title substring or top-level window title when target=window.
`device`	Yes	ReMCP device id returned by list_devices. Required for every device operation.
`target`	No	Optional target type. auto prefers native accessibility, then browser DOM/CDP, then OCR/coordinates where supported. Use window for explicit top-level window focus/text/scroll targeting.
`ocr_text`	No	Visible text to find in rendered pixels for the OCR click fallback.
`selector`	No	CSS selector when the fallback target is a browser element.
`window_id`	No	Top-level window id returned by list_windows when target=window.
`browser_text`	No	Visible browser text used only to locate a DOM target; for action=type, text remains the value to enter.
`window_title`	No	Limit matching to a top-level accessibility window/frame title substring when available.
`automation_id`	No	Windows AutomationId when available.

Output Schema

Name	Required	Description	Default
`data`	No	Computer action structured result for computer_action. Stable fields are declared explicitly; platform-specific fields may be added. Large results may return truncated/bytes/preview instead of the full payload.
`text`	Yes	Concise human-readable result of the tool call.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 19, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false; the description adds meaningful behavioral context by clarifying that focusing is non-activating (no typing/button activation), which resolves ambiguity about side effects. It doesn't cover return values, but the output schema exists.

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?

Two tightly worded sentences with zero waste, and the primary action is front-loaded ahead of the limitation caveat.

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?

For a complex 17-parameter tool with an output schema and full schema coverage, the description supplies the essential behavioral framing. It doesn't explain target-type tradeoffs in depth, but structured fields fill that gap.

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 100%, so all 17 parameters are already documented in the schema. The description adds no parameter-level detail beyond 'semantic target', leaving the schema to carry the burden. Baseline 3 is correct.

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 specific verb and resource ('bring an identified native desktop control into focus'), which implicitly distinguishes it from browser_focus and window_focus by specifying 'native desktop control'. It doesn't explicitly name those siblings, so differentiation is inferred rather than stated.

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?

Clear context: 'before typing or interacting with it' establishes the when, and 'Prefer a current semantic target' gives selection guidance. The caveat 'focusing alone does not type text or activate a button' rules out misuse, though no siblings are named as alternatives.

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

All ReMCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?