Skip to main content
Glama

google_images

Retrieve Google Images search results with titles, thumbnails, source links, and original dimensions. Supports filters for size, color, type, date, and license.

Instructions

Retrieves Google Images search results including titles, thumbnails, source links, and original image dimensions. Each successful request costs 10 API credits. [Credits: 10 API credits per successful request] Notes: Time filtering: use either period_unit+period_value OR start_date/end_date, not both together with tbs's own date components (each overrides the corresponding tbs component). chips values are discovered from a prior response's suggested_searches array. Returns: { images_results: [{title, image, source, original, link, original_height, original_width, original_size, rank}] }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
crNoRestrict search to specific countries, formatted country{2-letter uppercase code}, pipe-separated for multiple, e.g. countryFR|countryDE.
lrNoLimit search to one or multiple languages, formatted lang_{language code}.
tbsNoAdvanced parameter ('to be searched') to filter search results.
htmlNoReturn the full HTML of the Google Images page. (default: false)
nfprNoSet 1 to exclude auto-corrected/misspelled-query results, 0 to include them. (default: 0)
pageNoPage number of Google search results. 0 = first page, 1 = second page, etc. (default: 0)
safeNoAdult content filter. Allowed values: active, off. (default: off)
uuleNoEncoded geographic location/locale to tailor results, e.g. w+CAIQIFJlbGF5IFN0YXRlcw==.
chipsNoFilters results using a Google-suggested search term (e.g. 'red apple'). Suggested chips appear under suggested_searches in the response when ijn=0; each includes a chip value and a scrapingdog_link.
imgarNoImage aspect ratio filter. Allowed values: s (Square), t (Tall), w (Wide), xw (Panoramic).
imgszNoImage size filter. Allowed values: l (Large), m (Medium), i (Icon), qsvga (>400x300), vga (>640x480), svga (>800x600), xga (>1024x768), 2mp, 4mp, 6mp, 8mp, 10mp, 12mp, 15mp, 20mp, 40mp, 70mp (Larger than N megapixels).
queryYesGoogle Search query. Example: query=pizza
domainNoGoogle domain for local results, e.g. google.co.in for India, google.co.uk for the UK. (default: google.com)
filterNoEnables/disables the 'Similar Results' and 'Omitted Results' filters. 1 (default) activates filters, 0 turns them off.
countryNoTwo-letter country code for the Google search (e.g. US, UK, FR). (default: us)
end_dateNoEnd date for the image search date range. Format YYYYMMDD, e.g. 20241231. Cannot be used with period_unit/period_value. If start_date is blank, includes all dates before end_date. Overrides cdr/cd_max in tbs.
languageNoLanguage of the results, e.g. en, es, fr, de. (default: en)
licensesNoLicense filter. Allowed values: f (Free to use/share), fc (Free to use/share, even commercially), fm (Free to use/share/modify), fmc (Free to use/share/modify, even commercially), cl (Creative Commons), ol (Commercial and other licenses). Overrides the sur component of tbs.
image_typeNoImage type filter. Allowed values: face, photo, clipart, lineart, animated. Overrides the itp component of tbs.
start_dateNoStart date for the image search date range. Format YYYYMMDD, e.g. 20241201. Cannot be used with period_unit/period_value. If end_date is blank, range extends to today. Overrides cdr/cd_min in tbs.
image_colorNoImage color filter. Allowed values: bw, trans, red, orange, yellow, green, teal, blue, purple, pink, white, gray, black, brown. Overrides ic/isc components of tbs.
period_unitNoTime unit for retrieving recent images. Allowed values: s (Second), n (Minute), h (Hour), d (Day), w (Week), m (Month), y (Year). Cannot be used with start_date/end_date; takes precedence over the qdr component of tbs.
period_valueNoDuration used with period_unit, e.g. 15 seconds, 42 hours, 178 days. Valid range 1 to 2,147,483,647. (default: 1)
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses the cost (10 credits), return structure, and important parameter interactions (mutual exclusivity of date parameters, chips from suggested_searches). It does not cover rate limits or authentication, but given the complexity, it provides substantial behavioral insight.

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?

The description is informative and front-loaded with purpose, but it contains a slight redundancy (credit mentioned twice). It is structured with clear notes, but could be more concise. Overall, it earns its place without being overly verbose.

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?

Given the complexity (23 parameters, no output schema, no annotations), the description covers key behavioral aspects: cost, return format, and parameter constraints. It does not detail every edge case, but it provides sufficient contextual completeness for an agent to use the tool effectively.

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 the schema already documents all parameters. The description adds meaningful semantic guidance beyond the schema, such as the chips discovery mechanism and the constraints on time filtering parameters. This extra context helps an agent use the parameters correctly, elevating it above the baseline of 3.

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?

The description clearly states the tool retrieves Google Images search results including specific fields like titles, thumbnails, source links, and dimensions. It distinguishes from sibling tools such as google_search, google_videos, and google_lens, which handle different media or search types. The verb 'retrieves' is specific and actionable.

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?

The description mentions cost (10 API credits per request) and provides notes on time filtering and chips usage. However, it does not explicitly contrast with siblings or state when to use this tool vs. alternatives like google_search or google_lens. While some guidance is implied, it lacks explicit when-to-use/when-not-to-use direction.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/alessandrobenigni/ScrapingDog-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server