Glasswarp

screen.observe

Read-only

Read the current screen: UIA targets (numbered ids + native coords) and a text summary. Does not move mouse/keyboard. Default image=false (no JPEG) for speed; set image=true only when you must judge pixels visually (then max_width≈960, quality≈60). If changed=false, JPEG is omitted even when requested — do not re-analyze; wait or act differently. If dirty is null, assume changed. Prefer input.send_actions for multi-step UI; observe after meaningful steps, not after every click. Target ids are valid only until the next UI change.

Input Schema

TableJSON Schema

Name	Required	Description
`mark`	No	Overlay numbered targets on JPEG when image=true (default true; ignored if image=false)
`image`	No	Include JPEG (default false). True only to visually read/judge the screen.
`quality`	No	JPEG quality 40–100 when image=true (default 60)
`max_width`	No	JPEG max width when image=true (default 960). Clicks always use native coords, not JPEG pixels.
`session_id`	Yes	Active session id from session.start

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	False when the tool failed
`changed`	No	Whether the frame changed since last observe; null if unknown
`message`	Yes	Human-readable observe summary / targets
`has_image`	No	True when a JPEG was included in the MCP content
`native_width`	No	Native capture width
`native_height`	No	Native capture height

TDQS

A5/5.0

Behavior5/5

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

Beyond readOnlyHint and openWorldHint annotations, the description adds key behaviors: no mouse/keyboard movement, target id validity, image suppression on changed=false. All disclosed clearly.

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?

Front-loaded with purpose, then concise bullet-style guidance. Every sentence serves a purpose; no wasted words despite richness.

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?

Given 5 parameters, 1 required, and existence of output schema, the description completely covers usage, parameter decisions, and behavioral constraints. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the description still adds value: default values, when to enable image, approximate max_width/quality, and mark behavior. No redundancy.

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 clearly states 'Read the current screen' with a specific verb and resource, listing outputs (UIA targets, text summary) and distinguishing sibling tools like input.send_actions.

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?

Explicit guidance: prefer input.send_actions for multi-step UI, observe after meaningful steps, when to set image=true, and how to handle the changed flag (do not re-analyze). No ambiguity.

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

All Glasswarp tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: session management, input methods, screen observation, demo retrieval, and rig listing. Descriptions explicitly state when to prefer one over another (e.g., click_target over click_xy, send_actions over chaining). No two tools overlap in functionality.

Naming Consistency5/5

All tools follow the domain.verb_noun pattern (e.g., app.launch, input.click_target, session.start) with consistent snake_case. Verbs like launch, list, get, click, send, type, observe are clear actions, and the naming is predictable across the entire set.

Tool Count5/5

16 tools cover the full spectrum of remote desktop control: 2 for demos, 1 for rigs, 4 for sessions, 1 for screen, 7 for input, and 1 for app launching. Each tool is necessary and there is no redundancy; the count is well-scoped for the domain.

Completeness5/5

The tool set provides a complete lifecycle for remote desktop interaction: rig selection, session start/end, screen observation, all common input actions (click, type, scroll, drag, multi-step sequences), app launching, and demo retrieval. There are no obvious gaps for typical UI automation tasks.

screen.observe

Input Schema

Output Schema

TDQS

Glama MCP Gateway

TDQS

Resources