Skip to main content
Glama

CrawlerData: Google Shopping & SERP

Google Images

google_images
Read-only

Google Images results: image URL, thumbnail, title, source page and size. 1 credit.

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": {
      "query": "<query>"
    },
    "name": "google_images"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoSearch from a point: its latitude in degrees, e.g. 40.7580. Give lat and lng together, instead of location or uule; set country to the point's country (default "us").
lngNoSearch from a point: its longitude in degrees, e.g. -73.9855. Give lat and lng together.
pageNo
uuleNoAdvanced: a raw Google uule value ("w+...", "a+...", "j+..."), plain or URL-encoded as copied from a Google URL. Use location instead unless you already have uule values.
queryYes
countryNoTwo-letter country code. Defaults to "us", or to the country of location.
languageNoen
locationNoSearch from a city, region or postal code: a Google canonical location name, "City,Region,Country" (Google Ads geotarget format), e.g. "Austin,Texas,United States". When country is omitted it is taken from the location.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / lat
      Added value: +{
      +  "description": "Search from a point: its latitude in degrees, e.g. 40.7580. Give lat and lng together, instead of location or uule; set country to the point's country (default \"us\").",
      +  "maximum": 90,
      +  "minimum": -90,
      +  "type": "number"
      +}
    • addedInput schema / properties / lng
      Added value: +{
      +  "description": "Search from a point: its longitude in degrees, e.g. -73.9855. Give lat and lng together.",
      +  "maximum": 180,
      +  "minimum": -180,
      +  "type": "number"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / uule / description
      Previous value: -"Advanced: a raw Google uule value (\"w+...\", \"a+...\", \"j+...\"), sent as is. Use location instead unless you already have uule values."New value: +"Advanced: a raw Google uule value (\"w+...\", \"a+...\", \"j+...\"), plain or URL-encoded as copied from a Google URL. Use location instead unless you already have uule values."
    • removedInput schema / properties / uule / pattern
      Removed value: -"^[A-Za-z][+ ][A-Za-z0-9+/_=-]{4,1000}$"
  3. Changed2 schema fields changed
    • changedInput schema / properties / uule / description
      Previous value: -"Advanced: a raw Google uule value, sent as is. Use location instead unless you already have uule values."New value: +"Advanced: a raw Google uule value (\"w+...\", \"a+...\", \"j+...\"), sent as is. Use location instead unless you already have uule values."
    • changedInput schema / properties / uule / pattern
      Previous value: -"^[aw][+ ][A-Za-z0-9+/_=-]{4,1000}$"New value: +"^[A-Za-z][+ ][A-Za-z0-9+/_=-]{4,1000}$"
  4. First observed

TDQS

B3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and open-world nature are covered. The description adds genuinely new behavioral information in '1 credit', which tells the agent about cost per call and encourages batching. It omits result-count and pagination behavior, which matters for a tool with a 'page' parameter.

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?

A single compact sentence, front-loaded with the resource and followed by the payload fields and cost. Nothing is wasted, though the terseness leaves the coverage gaps noted above rather than being a model of efficient completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter tool with no output schema, the description is thin: it never explains pagination, result volume, or why location/lat/lng/uule exist. The field list partially substitutes for a missing output schema and the credit note is useful, but key invocation context is absent.

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

Parameters2/5

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

Schema description coverage is 63% and the description adds no parameter meaning whatsoever. Notably the required 'query' parameter has no schema description at all, and the description never states that the image search is driven by a text query, nor how 'page' affects results.

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 names the resource ('Google Images results') and enumerates the returned fields (image URL, thumbnail, title, source page, size), so an agent knows this surfaces image results rather than web, news, or local results. It never explicitly contrasts itself with siblings like google_search or google_news, so differentiation rests on the tool name alone.

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

Usage Guidelines2/5

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

There is no when-to-use guidance: nothing says to pick this over google_search when the user wants images, nor any prerequisite or exclusion. The agent must infer the trigger condition entirely from the name.

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