Skip to main content
Glama

glass_wait_stable

Wait until a window settles (stops changing), then return the settled frame. Optionally restrict the settle check to a sub-region, or omit the image for a text-only result.

Instructions

Wait until the window stops changing, then return the settled frame. Optional stability_region watches only that sub-rectangle for settling (ignore unrelated motion); optional region crops the returned frame. Set include_image: false for a text-only {settled,width,height} result with no image (region ignored) — cheap before a text glass_diff.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ignoreNoWindow-relative rectangles to exclude from the settle comparison. Use for perpetually animating content — a blinking text caret, a clock, a spinner — which otherwise keeps the window from ever settling. Pixels inside a rect never count as changed and never set `saw_motion`. Combines with `stability_region`: rects are always window-relative and are intersected with it. Independent of `region`, which only crops the returned image. A rect that falls partially or entirely outside the compared area — the frame, or the `stability_region` sub-rectangle when one is set — is silently clamped or dropped, masking less than requested or nothing at all; the excluded count is reported as `ignored_pixels`, so a smaller-than-expected value flags a misplaced rect.
regionNoOptional window-relative sub-rectangle for the returned frame.
toleranceNoPer-channel difference (0–255) two frames may have and still count as unchanged (default 0, exact match). Raise it for a backend with dithering or compression noise.
window_idNoCapture/observe this window (id from `glass_list_windows`) instead of the active one, without changing which window subsequent ops target. Omit for the active window.
timeout_msNoGive up after this long (default 5000ms); returns `{settled:false}` rather than erroring.
interval_msNoHow long to wait between capture ticks (default 100ms).
include_imageNoReturn the settled frame as an image (default true). Set false for a text-only `{settled, saw_motion, observed_ms, ignored_pixels, width, height}` result with no WebP — cheap when the next step is a text `glass_diff`. `region` is ignored when false.
settle_framesNoConsecutive unchanged frames required before the UI counts as settled (default 3). Raise it for an app that pauses mid-animation.
stability_regionNoOptional window-relative sub-rectangle to watch for settling; when set, the settle decision ignores changes outside it. Independent of `region`.
Behavior3/5

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

With no annotations, the description discloses the wait behavior and option interactions. However, it inaccurately summarizes the text-only return fields as `{settled,width,height}` when the schema documents `{settled, saw_motion, observed_ms, ignored_pixels, width, height}`. It also omits mention of timeout behavior, though the schema covers it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the core purpose and then efficiently covers the key options. It is concise but slightly dense and uses a run-on structure; nonetheless, every clause earns its place.

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?

Despite the 9 parameters and no output schema, the description gives a solid high-level summary: waiting for stability, optional region cropping, and a text-only mode for cheap diffs. It does not mention all parameters, but the schema fully covers them. The slightly inaccurate return summary prevents a perfect score.

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 the baseline is 3. The main description mentions stability_region, region, and include_image with some context, but these details already appear in the schema descriptions. No additional semantic value is added for parameters.

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 the tool waits until the window stops changing and returns the settled frame. This specific verb+resource+outcome distinguishes it from sibling wait tools like glass_wait_for_region or glass_wait_for_log.

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?

It provides clear context for using the tool, such as using stability_region to ignore unrelated motion and setting include_image to false for a cheap text-only result before a text glass_diff. It does not explicitly name alternatives or exclusions, but the usage intent is clear.

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

Install Server

Other Tools

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/fixed-width/glass'

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