Skip to main content
Glama

Google Lens

google_lens
Read-only

Analyze images using Google Lens. Upload an image URL to get visual matches, web results, product identification, text extraction, and exact match detection. Supports refining results with a text query for search types: all and visual_matches. A result whose link is a Google redirect carries a token beside it: if google_resolve is among your tools, pass the token to it for the destination URL.

Required: url (a publicly accessible image URL).

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": {
      "url": "<url>"
    },
    "name": "google_lens"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoOptional text query to refine image search results. Only works with search_type: all or visual_matches.
urlYesPublic URL of the image to analyze. Required.
cropNoCrop region as left;top;right;bottom with normalized 0-1 coordinates (e.g., '0.1;0.2;0.6;0.8'). Searches only the specified region of the image.
countryNoCountry code for localized results (e.g., 'us', 'gb'). Uses ISO 3166-1 alpha-2 format.
safe_searchNoSafe search filtering. 'active' enables strict filtering, 'blur' blurs explicit content (default), 'off' disables filtering.
search_typeNoType of lens analysis. 'all' for general analysis, 'visual_matches' for similar images (some carry price and stock), 'exact_matches' for identical images. Default: all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / q / description
      Previous value: -"Optional text query to refine image search results. Only works with search_type: all, visual_matches, or products."New value: +"Optional text query to refine image search results. Only works with search_type: all or visual_matches."
    • changedInput schema / properties / search_type / description
      Previous value: -"Type of lens analysis. 'all' for general analysis, 'visual_matches' for similar images, 'products' for shopping, 'exact_matches' for identical images. Default: all."New value: +"Type of lens analysis. 'all' for general analysis, 'visual_matches' for similar images (some carry price and stock), 'exact_matches' for identical images. Default: all."
    • changedInput schema / properties / search_type / enum
      Previous value: -[
      -  "all",
      -  "visual_matches",
      -  "products",
      -  "exact_matches"
      -]New value: +[
      +  "all",
      +  "visual_matches",
      +  "exact_matches"
      +]
  2. Changed1 schema field changed
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
  3. Changed2 schema fields changed
    • changedInput schema / properties / safe_search / description
      Previous value: -"Safe search filtering. 'blur' blurs explicit content (default), 'off' disables filtering."New value: +"Safe search filtering. 'active' enables strict filtering, 'blur' blurs explicit content (default), 'off' disables filtering."
    • changedInput schema / properties / safe_search / enum
      Previous value: -[
      -  "blur",
      -  "off"
      -]New value: +[
      +  "active",
      +  "blur",
      +  "off"
      +]
  4. Changed1 schema field changed
    • addedInput schema / properties / crop
      Added value: +{
      +  "description": "Crop region as left;top;right;bottom with normalized 0-1 coordinates (e.g., '0.1;0.2;0.6;0.8'). Searches only the specified region of the image.",
      +  "type": "string"
      +}
  5. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive, not idempotent), so the description correctly spends its words elsewhere: it discloses the categories of result returned and the non-obvious redirect-token behavior that annotations cannot express. What it does not say is anything about response shape or how large/heavy a Lens call is, leaving a modest gap.

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?

Four sentences, front-loaded with purpose and results, then constraints, then the redirect-token caveat, and finally the required-parameter reminder. Tight and ordered; only the trailing 'Required: url' sentence borders on redundant given the schema already marks it required.

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?

For a six-parameter, read-only, open-world tool with no output schema, the definition covers what comes back at a category level, the query/search_type coupling, and the redirect chaining rule. An agent could invoke it correctly from this text alone; only a finer sketch of the result structure is absent.

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 every parameter, including both enums, is documented there. The description only restates the required 'url' and the q/search_type restriction, adding essentially no syntax or format meaning beyond the schema. Baseline 3 applies.

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?

Opens with a specific verb+resource ('Analyze images using Google Lens') and enumerates what the caller gets back (visual matches, web results, product identification, text extraction, exact match detection). That is far beyond tautology, but it never names or contrasts with a sibling like google_images_light or google_product, so an agent still has to infer which image tool 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 Guidelines4/5

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

Gives concrete operational guidance: the image must be a publicly accessible URL, the text query only refines search_type 'all' or 'visual_matches', and the redirect-token sentence tells the agent exactly when and how to chain into google_resolve. It stops short of stating when to prefer this tool over alternatives, so it is clear context without exclusions.

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