Skip to main content
Glama

Searchapi

by io.searchapi
OverviewDiscussionsAdmin

Google Ai Mode

google_ai_mode
Read-only

Get Google's AI-generated responses (AI Overviews) with source citations and reference links.

Two ways to call:

  • Text search — requires q.

  • Image analysis — requires url; optionally include q to ask a question about the image.

To ask a follow-up, pass the conversation_token from the previous response along with the next question in q. The answer then keeps the context of the earlier turns.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoSearch query for AI-generated response. Required if url not provided. Cannot exceed 8193 characters.
urlNoPublic image URL. Required if q not provided. Include q to ask a specific question about the image.
locationNoGeographic location for localized results.
conversation_tokenNoContinues a previous conversation. Pass the pagination.conversation_token returned by the last response together with the follow-up question in q. Omit it to start a new conversation. Cannot be combined with url.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / conversation_token
      Added value: +{
+  "description": "Continues a previous conversation. Pass the pagination.conversation_token returned by the last response together with the follow-up question in q. Omit it to start a new conversation. Cannot be combined with url.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / url
      Added value: +{
+  "description": "Public image URL. Required if q not provided. Include q to ask a specific question about the image.",
+  "type": "string"
+}
  3. Changed1 schema field changed
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
  4. Changed1 schema field changed
    • changedInput schema / properties / q / description
      Previous value: -"Search query for AI-generated response. Required if url not provided."New value: +"Search query for AI-generated response. Required if url not provided. Cannot exceed 8193 characters."
  5. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint=false and destructiveHint=false, covering the safety and side-effect profile. The description adds the multi-turn context-retention behavior, but that is largely a restatement of the conversation_token schema text, and it says nothing about rate limits, auth, or response latency.

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 purpose is front-loaded in the first sentence, followed by a compact mode list and a short follow-up note; no sentence is wasted. The 'Two ways to call' block partially duplicates schema constraints, which keeps it from being perfectly tight.

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 helpfully characterizes the return as 'source citations and reference links', and it covers both input modes plus the multi-turn flow for all four parameters. It is nearly complete, missing only edge-case handling such as what happens when both q and url are supplied or when conversation_token is combined with url.

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 baseline is 3, but the description does add value by synthesizing the four parameters into an actionable either/or structure ('Two ways to call') and by explaining the follow-up chaining of conversation_token with a new q. The mutual-exclusivity and continuation semantics are therefore clearer than reading four separate schema descriptions.

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 a specific verb and resource — 'Get Google's AI-generated responses (AI Overviews) with source citations' — which is a distinct artifact from the sibling google_search_light or google_lens results. It does not, however, explicitly name any sibling or state how it differs from a plain web search, so the differentiation must be inferred from the phrase 'AI-generated responses'.

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?

It clearly enumerates two calling modes and their prerequisites ('Text search — requires q', 'Image analysis — requires url; optionally include q'), plus the condition for continuing a conversation. It gives no exclusions or named alternatives (e.g., when to prefer google_search_light or google_lens), so the routing guidance is clear but not complete.

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

All Searchapi toolsInspect
Try in Browser
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources