Skip to main content
Glama

google-image-search

by com.jojapi
OverviewDiscussionsAdmin

Search Images

get_v2

Google Images results for a query, twenty a page: for each image its URL, width and height, its thumbnail with width and height, and the page it is on. response.next_cursor fetches the next twenty (null after the last page). Billing per call: 1 Credits.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qYesSearch query. Google's search operators work: `adele site:youtube.com`, `intitle:paris`, `query -exclude`.
hlNoInterface language code. Default: en
tbsNoGoogle's image filters, e.g. `isz:l` (large), `itp:face` (faces), `ic:gray` (black and white), `qdr:w` (past week).
nfprNo`1` searches exactly the query as typed, without Google's spelling correction.
safeNoSafeSearch: `active` filters explicit results, `off` does not.
cursorNoThe `next_cursor` of a previous answer, unchanged, for the next twenty images.
filterNo`0` includes the results Google omits as very similar to others.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / suggestion_query
      Removed value: -{
-  "description": "Deprecated; accepted and ignored (suggestions are no longer returned).",
-  "title": "suggestion_query",
-  "type": "string"
-}
  2. Changed10 schema fields changed
    • changedInput schema / properties / cursor / description
      Previous value: -"Cursor for next results."New value: +"The `next_cursor` of a previous answer, unchanged, for the next twenty images."
    • addedInput schema / properties / filter / description
      Added value: +"`0` includes the results Google omits as very similar to others."
    • changedInput schema / properties / hl / description
      Previous value: -"Language code for search. Default: en"New value: +"Interface language code. Default: en"
    • addedInput schema / properties / nfpr / description
      Added value: +"`1` searches exactly the query as typed, without Google's spelling correction."
    • changedInput schema / properties / q / description
      Previous value: -"Search query. You can use search parameters.\n\ne.g. `adele site:youtube.com`\ne.g. `query -exclude`"New value: +"Search query. Google's search operators work: `adele site:youtube.com`, `intitle:paris`, `query -exclude`."
    • changedInput schema / properties / safe / description
      Previous value: -"If you want safe search, set it to `active`"New value: +"SafeSearch: `active` filters explicit results, `off` does not."
    • addedInput schema / properties / safe / example
      Added value: +"active"
    • changedInput schema / properties / suggestion_query / description
      Previous value: -"Suggestion query (must be taken from response suggestions)."New value: +"Deprecated; accepted and ignored (suggestions are no longer returned)."
    • changedInput schema / properties / tbs / description
      Previous value: -"Search filters."New value: +"Google's image filters, e.g. `isz:l` (large), `itp:face` (faces), `ic:gray` (black and white), `qdr:w` (past week)."
    • addedInput schema / required
      Added value: +[
+  "q"
+]
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the pagination termination signal (null after the last page) and the cost model (1 Credit per call). It omits auth requirements, rate limits, and error behavior, but the cost and cursor semantics are genuinely useful disclosures.

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 dense sentences, front-loaded with the returned payload, followed by pagination and billing. No filler and every sentence carries distinct information.

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?

There is no output schema, so the description must describe the return shape — and it does, listing URL, dimensions, thumbnail dimensions, and page position. Combined with the pagination and cost notes, an agent has what it needs to call and consume this tool.

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%, so the schema already documents all seven parameters (including operator syntax, safe search, tbs filters). The description adds only the cursor-pagination meaning, which the schema's `cursor` description also covers. Baseline 3 is appropriate.

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?

States a specific verb and resource — 'Google Images results for a query' — and enumerates the returned fields, so an agent knows exactly what it gets. It does not, however, differentiate itself from the sibling get_v1, leaving ambiguity about which to pick.

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?

The description explains pagination mechanics (`response.next_cursor` for the next twenty, null on the last page) but gives no when-to-use guidance or any condition distinguishing it from get_v1. Usage is left to inference.

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

All google-image-search toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources