Skip to main content
Glama

Google Images Light

google_images_light
Read-only

Search Google Images for photos and visual content. Returns image results with thumbnails, source pages, and original image URLs. Useful for finding reference images, illustrations, and visual content.

Each image has a related_content_id: pass it, with the same q, to google_images_related_content for the related images, products and searches Google shows for that image.

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": {
      "q": "<q>"
    },
    "name": "google_images_light"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesImage search query. Required.
glNoISO 3166-1 alpha-2 country code in lowercase (e.g., 'us', 'gb', 'de'). Default: us.
pageNoPage number for pagination. Default: 1.
sizeNoFilter by image size.
colorNoFilter by dominant color.
image_typeNoFilter by image type.
time_periodNoFilter images by recency.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed1 schema field changed
    • changedInput schema / properties / gl / description
      Previous value: -"Country code for search context (e.g., 'us', 'gb'). Default: us."New value: +"ISO 3166-1 alpha-2 country code in lowercase (e.g., 'us', 'gb', 'de'). Default: us."
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld, non-idempotent and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: it enumerates the return payload shape and documents the related_content_id chaining workflow, including that the same q must be reused. It stops short of mentioning result caps, pagination depth, or rate limits.

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?

Two short paragraphs: purpose plus return summary, then a front-loaded workflow note. Every sentence is useful, though 'Returns image results with thumbnails, source pages, and original image URLs' and 'Useful for finding reference images, illustrations, and visual content' partially overlap in framing the same idea.

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 does the right thing by summarizing the return payload, and all seven parameters are fully documented in the schema. The main residual gap for an open-world, paginated search tool is the absence of any note on pagination behavior or how many pages are practically retrievable.

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% and four filters are enums with self-explanatory values, so the schema carries the parameter burden. The description adds only one piece of semantic value beyond it — that related_content_id must be passed together with the same q — and says nothing about how page, size, color, image_type, or time_period interact or compose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Search Google Images for photos and visual content,' and states what is returned (thumbnails, source pages, original image URLs). It implicitly separates itself from the text web search sibling by naming Google Images specifically, though it never explicitly contrasts with google_lens, the closest visual-search sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives positive context ('Useful for finding reference images, illustrations, and visual content') and a concrete follow-up route to google_images_related_content with the required q pairing. However, there is no guidance on when to prefer this over google_lens or google_search_light, and no exclusions or preconditions are stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources