Update gemini_investigate tool description: hard cap is now 20, not 10

Author: allocsys

connectors/gemini/tools.js

@@ -98,7 +98,7 @@ export function register(server) {
     "Delegate an open-ended, multi-step READ-ONLY investigation to Gemini instead of doing it yourself one tool call at a time. Gemini runs its own loop server-side -- reading GitHub files/trees/commits, Cloudflare Workers logs, and Notion pages/databases across as many turns as it needs (bounded by max_steps) -- and returns one synthesized answer. Use this for things like \"why is CI failing on PR #42\" or \"summarize what changed in this repo over the last week\" where you'd otherwise need 5-10 separate manual tool calls. Not for anything requiring a write -- this tool is read-only by design.",
     {
       task:          z.string().describe("The investigation task/question, described with enough context (repo names, time ranges, etc.) for Gemini to act without needing to ask you anything back -- it can't."),
-      max_steps:     z.number().optional().describe("Max tool-use turns Gemini gets before being forced to answer (default 6, hard cap 10 regardless of this value)."),
+      max_steps:     z.number().optional().describe("Max tool-use turns Gemini gets before being forced to answer (default 6, hard cap 20 regardless of this value)."),
       log_to_notion: z.boolean().optional().describe("Whether to log the task, step-by-step tool calls, and final answer as a page under the Gemini section of Notion (default: true). Write always targets the fixed Gemini root page."),
     },
     async ({ task, max_steps = 6, log_to_notion = true }) => {