post_dataforseo_ai_gemini_llm_scraper_liveLive Gemini LLM Scraper endpoint provides structured results from Gemini. The results are specific to the selected location (see the List of Locations), language (see the List of Languages), and keyword.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / properties / body / items / properties / location_code / descriptionPrevious value: -"search engine location code required field if you don't specify location_name if you use this field, you don't need to specify location_name you can receive the list of available locations of the search engines with their location_code by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/gemini/llm_scraper/locations example: 2840"New value: +"search engine location code required field if you don't specify location_name or location_coordinate if you use this field, you don't need to specify location_name or location_coordinate you can receive the list of available locations of the search engines with their location_code by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/gemini/llm_scraper/locations example: 2840"Input schema / properties / body / items / properties / location_coordinate / descriptionPrevious value: -"Search location as latitude,longitude,radius. Use instead of location_name or location_code."New value: +"GPS coordinates of a location required field if you don't specify location_name or location_code if you use this field, you don't need to specify location_name or location_code location_coordinate parameter should be specified in the \"latitude,longitude,radius\" format the maximum number of decimal digits for \"latitude\" and \"longitude\": 7 the minimum value for \"radius\": 199 (mm) the maximum value for \"radius\": 199999 (mm) example: 53.476225,-2.243572,200"Input schema / properties / body / items / properties / location_name / descriptionPrevious value: -"full name of search engine location required field if you don't specify location_code if you use this field, you don't need to specify location_code you can receive the list of available locations of the search engine with their location_name by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/gemini/llm_scraper/locations example: United States"New value: +"full name of search engine location required field if you don't specify location_code or location_coordinate if you use this field, you don't need to specify location_code or location_coordinate you can receive the list of available locations of the search engine with their location_name by making a separate request to the https://api.dataforseo.com/v3/ai_optimization/gemini/llm_scraper/locations example: United States"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, and idempotentHint=false, but the description adds nothing behavioral on top of that — it says nothing about cost per request, live-vs-task semantics, rate limits, or why a 'scraper' would be flagged destructive. For a POST live endpoint with an unusual annotation profile, this is a real gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with no padding and the core purpose front-loaded. It is efficient, though the second sentence mostly restates filtering dimensions already implied by the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values need not be described, but the tool has a nested array-of-objects body with multiple anyOf constraints and no usage or behavioral context is supplied to compensate. Given the complexity and the long list of near-duplicate Gemini siblings, this description is insufficient for correct selection and invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is reported as 0%, so the description must compensate, and it only alludes to 'location', 'language', and 'keyword' generically. It does not explain the anyOf requirement (exactly one of location_name/location_code/location_coordinate and one of language_name/language_code), the tag field, or the %-decoding rules for keyword.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names the resource (Gemini LLM scraper) and says it returns structured results filtered by location, language, and keyword. However, it never distinguishes this tool from its close siblings post_dataforseo_ai_gemini_llm_responses_live or post_dataforseo_ai_gemini_llm_scraper_live_html, so an agent cannot tell which Gemini endpoint to pick without opening the schemas.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to use this tool versus the LLM responses live endpoint, the HTML scraper variant, or any of the other AI optimization tools. The only hint of context is that results depend on location/language/keyword, which is a description of output, not of usage conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.