Skip to main content
Glama

screenshot_query

List cached screenshots by metadata (capture ID, dimensions, size, timestamp, tag/window) without re-reading pixels. Filter, page, and find prior captures before reclaiming cache space.

Instructions

List screenshots already saved in the disk-cache WITHOUT re-reading any pixels. The screenshot tools return each capture as a cheap by-ref link (screenshot://by-ref/{captureId}); this lists what is in the cache — captureId + by-ref uri, dimensions, size in bytes, timestamp, and tag/window — so you can find and re-open a specific earlier capture, or check how much the cache holds before reclaiming space with screenshot_gc. The response also carries whole-cache totals (totalCaptures / totalBytes). Reading a capture's bytes still costs tokens, so open a by-ref link only when you actually need to inspect the pixels. Filter by tag (case-insensitive) / windowUuid / since / until; page with limit (default 50) and offset. Results are newest-first and never include a filesystem path.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagNoFilter to captures stored under this tag (case-insensitive). Omit to list all.
limitNoMaximum rows to return, newest first (default 50, max 500).
sinceNoOnly captures taken at/after this time (epoch milliseconds, inclusive).
untilNoOnly captures taken at/before this time (epoch milliseconds, inclusive).
offsetNoRows to skip from the newest end, for paging (default 0).
includeNoOptional response-shape opt-in. `['envelope']` returns the self-documenting envelope (`_version` / `data` / `as_of` / `confidence`). `['raw']` forces raw shape (overrides DESKTOP_TOUCH_ENVELOPE=1 server default). Default behaviour is raw shape (compat with existing clients).
windowUuidNoFilter to captures of a specific window (the window's stable id).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv2.3.1
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / offset / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / since / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / since / minimum
      Added value: +-9007199254740991
    • addedInput schema / properties / until / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / until / minimum
      Added value: +-9007199254740991
  2. Addedv1.12.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers: the by-ref link return convention (screenshot://by-ref/{captureId}), the fact that reading bytes costs tokens, newest-first ordering, whole-cache totals in the response, and that results never include a filesystem path. It does not cover auth/rate limits, but the behavioral profile is unusually complete.

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?

Front-loaded with the core purpose, then the response shape, then filtering/paging, then the ordering guarantee. Dense with many parentheticals, but each sentence carries information an agent needs. Slightly overpacked but not wasteful.

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?

No output schema exists, so the description compensates by enumerating the returned fields (captureId + by-ref uri, dimensions, size in bytes, timestamp, tag/window) and the totals (totalCaptures/totalBytes), plus ordering. Nothing an agent needs to call this correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds real meaning beyond the schema: it groups the filters (tag/windowUuid/since/until), states the paging defaults (limit default 50, offset), and clarifies that results are newest-first and offset skips 'from the newest end', which disambiguates the offset direction the schema leaves implicit.

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 a specific verb and resource ('List screenshots already saved in the disk-cache') and sharpens it with a distinguishing constraint ('WITHOUT re-reading any pixels'). It also implicitly separates this from sibling `screenshot` (which captures) and names `screenshot_gc` as the space-reclaim alternative, so an agent can tell the tools apart without opening schemas.

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?

Explicitly gives the two motivating use cases ('find and re-open a specific earlier capture, or check how much the cache holds before reclaiming space with screenshot_gc') and names the alternative tool for space reclamation. It also adds an exclusion-style warning: open a by-ref link only when you actually need the pixels.

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