Skip to main content
Glama
Sign In
Autom MCP Server

Autom MCP Server

Official
by automdev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Google AI Mode

google_search_ai
Read-only

Query Google AI Mode via API to retrieve AI-generated answers, references, and shopping results as structured JSON for research, fact-checking, and product comparisons.

Instructions

Google AI Mode. Query Google AI Mode via API. JSON with text_blocks, references, and shopping_results. Credit cost: 3 credits per call.

Input Schema

NameRequiredDescriptionDefault
crNoLimit results to one or more countries. Use country{XX} with | as delimiter (e.g. countryFR|countryDE).
glNoCountry to use for the Google search. Two-letter country code (e.g. us for the United States, uk for United Kingdom, or fr for France).
hlNoLanguage to use for the Google search. Two or three-letter language code (e.g. en, es, fr), optionally followed by a region code (e.g. en-gb, es-419).
lrNoLimit results to one or more languages. Use lang_{xx} with | as delimiter (e.g. lang_fr|lang_de).
uuleNoGoogle encoded location parameter. Use for precise geo targeting. Note: uule and location cannot be used together.
queryYesThe question or search query you want Google AI Mode to answer (supports advanced operators like site:, inurl:, intitle:).
fieldsNoComma-separated list of fields to keep in the response, with dot notation for nested fields (e.g. name,location.city). Does not change the credit cost.
locationNoHuman-readable location to originate the search from (e.g. New York, NY, Paris, France). If several locations match, the most popular one is used. Note: location and uule cannot be used together.
google_domainNoGoogle domain to use for the search. Defaults to google.com. Default: "google.com".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description adds two genuinely useful facts beyond that: the billing impact (3 credits per call) and the shape of the payload (text_blocks, references, shopping_results). It says nothing about latency, rate limits, or failure modes for a live web-backed query.

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 terse sentences, front-loaded with purpose, then output shape, then cost. The opening fragment "Google AI Mode." largely repeats the title, but everything else earns its place.

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 nine parameters fully documented in the schema and no output schema, the description's brief note on returned fields (text_blocks, references, shopping_results) fills the main structural gap. What remains missing is the positioning against sibling search tools, which matters given the density of alternatives.

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 all nine parameters carry their own explanations, including the uule/location mutual exclusion and the cr/lr delimiter syntax. The description adds no parameter meaning beyond the schema, so the 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?

"Query Google AI Mode via API" gives a specific verb and a named branded resource, so an agent knows this hits Google's AI Mode endpoint. It never says how that differs from sibling google_search or google_search_light, so differentiation rests entirely on the product name.

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 explains when AI Mode is preferable to google_search, google_search_light, or duckduckgo_search, and no exclusions are stated. The only selection signal an agent gets is the 3-credit cost, which is presented without any comparison to cheaper siblings.

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

Deploy Server

Other Tools