Skip to main content
Glama

screenshot

Capture browser screenshots as viewable images or save PNG files, with full-page tiling for tall pages.

Instructions

Capture a screenshot. With no path it returns a viewable image (not base64 text); with a path it saves the PNG and returns the path. With tiles=true it slices a full-page capture into fixed-height tiles written to DISK (returns their paths + count, never base64) — for layout-heavy pages a vision-capable caller then reads tile-by-tile. Prefer reading the page text/selectors first — only screenshot when you actually need the pixels.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathNoOutput file path.
leaseNoOptional lease token to present if the target session is leased (0.7.0). Threaded per-call; never read from the server's env.
tilesNoSlice a full-page capture into fixed-height PNG tiles written to disk (0600); returns {tiles:[paths], count}. Implies full_page.
sessionNoOptional session name to target (omit for the shared 'default'). On a daemon shared with other agents, pass a UNIQUE name for stateful multi-step work (go→click→fill) so you don't collide on 'default'.
tile_dirNoDirectory for tile files (default: alongside path, else the screenshots cache).
full_pageNoFull page (not just viewport).
max_tilesNoCap the number of tiles (top of page first). Bounds output/disk, not decode memory. If omitted, defaults to VIBATCHIUM_MAX_TILES (60); when a tall page is capped the result carries truncated=true + total_tiles.
tile_heightNoTile height in px when tiles=true.
max_screenshot_pxNoCap the CAPTURED height (px) of a full-page/tiles shot — bounds the decode itself (the real memory driver on tall/infinite-scroll pages), not just tile count. Default VIBATCHIUM_MAX_SCREENSHOT_PX (30000); 0 disables. A taller page is captured to the top N px and the result carries height_truncated=true + captured_height_px + total_height_px.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A5/5.0
Behavior5/5

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

Discloses detailed behavioral traits beyond the openWorldHint annotation: return formats per mode (image vs path vs tiles path/count), never-base64 guarantee, truncation markers (truncated, height_truncated, captured/total heights), and lease token threading (never read from server env). This is far richer than the bare annotation.

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?

Though about 200 words, every sentence serves a purpose. It front-loads the core purpose, branches into modes, and integrates usage guidance and truncation semantics without wasted words. Structure is logical and scannable.

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 9 optional parameters and no output schema, the description covers all scenarios: image vs file vs tiles, disk output, truncation behavior, session uniqueness on shared daemons, and lease handling. Nothing an agent needs to call correctly is missing.

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?

Even with 100% schema coverage, the description adds critical meaning: tiles implies full_page, max_tiles bounds output/disk not decode memory, max_screenshot_px bounds decode itself, and defaults come from environment variables (VIBATCHIUM_MAX_TILES, VIBATCHIUM_MAX_SCREENSHOT_PX). This goes well beyond the schema's per-parameter descriptions.

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?

States 'Capture a screenshot' clearly as a verb+resource, then further specifies three modes (no path returns image, path saves PNG, tiles=true slices into tiles). It distinguishes itself from text-reading siblings by explicitly saying 'only screenshot when you actually need the pixels'.

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?

Provides explicit usage direction: 'Prefer reading the page text/selectors first — only screenshot when you actually need the pixels.' Also advises using tiles for layout-heavy pages so a vision-capable caller reads tile-by-tile, leaving no ambiguity about when to choose this tool over alternatives.

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