nexscope_data_ai_search_google_searchGoogle Research Tools: google Search API.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Google search keywords as `q=` parameter to initiate Google AI Mode search. Only a single round of dialogue is supported; if you need to ask questions, the agent needs to summarize the key information of the previous round of AI overview and splice new questions, and then initiate a request as a new `keyword`. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=false and openWorldHint=true, but the description adds nothing beyond them. It does not disclose that the call is a single-round AI Mode overview, that results cannot be conversed with (a critical behavioral constraint that only appears buried in the parameter schema), or what the response resembles. For a search tool with no output schema, the description carries the full burden and delivers none of it.
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?
Extremely short, but the brevity is under-specification rather than concision — one sentence that merely repeats the title and ends in a period. There is no front-loaded statement of purpose because there is no content to front-load.
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?
No output schema and no meaningful annotation coverage of behavior, yet the description does not explain what an AI Mode response contains, whether citations/sources are returned, or any limits. Completely inadequate for an open-world search tool an agent must decide to call.
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?
Single parameter with 100% schema description coverage, so the schema already explains the `q=` keyword and the single-round dialogue constraint in detail. The description adds no syntax, format, or query-construction guidance beyond what the schema provides; baseline 3 applies.
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 is a restatement of the tool title ('Google Research Tools: google Search API') and contains no verb describing what the tool actually does. Against dozens of sibling search tools (nexscope_google_ai_mode_search, nexscope_web_search, nexscope_seo_serp, nexscope_data_search_search), it offers no differentiation — the only hint that this is an AI Mode answer engine comes from the name token 'ai' and the schema, not the description.
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?
No guidance whatsoever on when to use this tool, when not to, or which sibling to prefer. An agent choosing between this and nexscope_google_ai_mode_search, nexscope_web_search, or nexscope_seo_serp gets zero signal from the description.
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.