Skip to main content
Glama

ghost_find

Locate UI elements by name, role, description, or on-screen text, returning center coordinates, bounding rectangle, and confidence. Works without focusing or raising the window, even when covered or on a hidden desktop.

Instructions

Locate an element (name|role|description|text) and return center (always), rect (has_rect=true for UIA/cache hits), source, confidence, name, escalated (true = a network VLM call was paid). Target window = window= (anchored) or the session anchor; else the foreground. Under the default background policy nothing is focused or raised: the lookup is scoped to the window's own UIA subtree, so it works while the window is covered or lives on a hidden desktop.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo'instant' (default): local tiers, auto-escalates to VLM on miss. 'deliberate': VLM from first attempt. 'instant_only': no VLM.
nameNoAccessible name (case-insensitive substring)
roleNoControl type: button, edit, checkbox, list, menu, tab, toolbar
textNoOn-screen text for OCR-based location
indexNoSelect the nth match (0-based) when several elements share the name/role; name+role AND-combine on this path; returns matches count
windowNoTitle substring of the window to search (anchors it). Omit to use the anchor.
descriptionNoNatural-language description for VLM grounding

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observedv0.23.4

TDQS

A4.2/5.0
Behavior5/5

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

With no annotations, this description carries the full behavioral burden and meets it: it discloses that center is always returned, rect is conditional on UIA/cache hits, escalated signals a paid VLM call, and the default policy never focuses or raises the target window. It also reveals that the lookup works on covered or hidden-desktop windows, which is non-obvious and important.

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 but each sentence earns its place: return contract, target-window precedence, and background policy. It is front-loaded with the core action and outputs and avoids filler.

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?

The description covers the essential return fields, scoping, and side-effect-free background behavior for a 7-parameter tool with no output schema. It stops short of fully complete by not stating failure/not-found behavior or making explicit that a locator parameter is expected despite all params being optional.

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 the baseline is 3. The description adds a little extra meaning by grouping locator strategies and clarifying the window= anchoring hierarchy, but it does not substantially extend what the schema already documents.

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 opens with a precise verb and resource: 'Locate an element' using name/role/description/text, and states the return contract. The mention of 'UIA subtree', window anchoring, and hidden desktops clearly separates this from browser/tab-based siblings such as ghost_tab_find.

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?

It gives useful context about target-window precedence and background behavior, implying it is for non-raising desktop UI lookups. It does not explicitly state when to prefer this over ghost_see, ghost_snapshot, or ghost_tab_find, nor does it list exclusions.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/NORTHTEKDevs/ghost'

If you have feedback or need assistance with the MCP directory API, please join our Discord server