Skip to main content
Glama

View image

read_image
Read-onlyIdempotent

View image files on your PC and return the picture for checking screenshots, UI renders, charts, or photos. Large images are downscaled on the PC without altering the original file.

Instructions

Look at an image file on this PC (PNG, JPEG, GIF, BMP, ICO, WebP): returns the picture itself, so you can check screenshots, UI renders, charts or photos the owner points you to. Large images are downscaled on the PC (maxSize, default 1600 px on the longer side; the file itself is not changed). Same folder rules as read_file; the owner may require approval because the picture leaves the PC.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "read_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoShort human-readable explanation (1 line, in the user's language) of what you are about to do and why. Shown to the user on the approval card. Always provide when calling mutating tools.
pathYes
agentNoShort consistent identifier or display name of this agent (e.g. 'Claude · Лендинг', 'Тесты', 'Мой агент'). Used to separate tasks and route tray messages when multiple agents work in parallel.
formatNoauto keeps JPEG photos as JPEG and everything else as PNG.
maxSizeNoLongest side in pixels after downscaling (default 1600).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare this a read-only, idempotent, non-destructive operation, but the description adds real behavioral context the annotations cannot: the image is downscaled on the PC with a default 1600 px long side, the source file is left unchanged, the owner may have to approve, and the picture leaves the machine. That last point is the kind of privacy/mutation-adjacent disclosure an agent needs before calling, though the response framing (single image object, failure modes for unsupported files) is unstated.

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?

Three sentences, each front-loaded with the highest-value fact in order: what it returns, how images are handled, then the permission caveat. No filler and no repetition of annotation data.

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?

With no output schema, the description carries the burden of return shape and does so ('returns the picture itself'), and it covers the approval and downscaling behaviors. Minor gaps remain: nothing about unsupported-file failures, size limits at the 4096 px ceiling, or how the agent learns the resulting dimensions.

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 80%, so the schema already documents maxSize, format, note, and agent. The description reinforces maxSize's default (1600 px on the longer side) and clarifies that downscaling does not modify the file, but it adds nothing about format, note, or agent semantics. Baseline 3 is appropriate.

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 ('Look at an image file on this PC'), enumerates supported formats (PNG, JPEG, GIF, BMP, ICO, WebP), and makes explicit that it returns the picture itself rather than metadata. That return-shape clause distinguishes it cleanly from read_file, which it names.

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?

Gives concrete use cases (screenshots, UI renders, charts, photos the owner points you to) and routes folder/permission questions to read_file's rules instead of restating them. It lacks an explicit 'use read_file instead when...' exclusion, so it falls short of a 5.

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