fix(templates): search templates stop probing with searches; add firecrawl

Readiness probes ran real searches every interval: searxng's
searxng_web_search probe fanned a query out to every engine 1,440 times a
day, billing API-key engines (braveapi, kagi), and duckduckgo's `search`
probe scraped DuckDuckGo from the same IP agents search from.

- searxng: probe searxng_instance_info, which reads /config only
- duckduckgo: probe fetch_content on example.com every 300s
- firecrawl (new): firecrawl-mcp against a self-hosted or cloud
  Firecrawl, for reading pages as main-content markdown; probe
  firecrawl_scrape on example.com every 300s

Every probe still names a readiness tool, as templates.test.ts requires;
each was run against the real package before being written down.
docs/web-search.md now pairs searxng (search) with firecrawl (reading)
and says why duckduckgo does not hold up under agent traffic.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JPjtnE6Gd343oRNtMU9Bcd

templates/searxng.yaml

@@ -4,10 +4,12 @@ description: SearXNG MCP server for private web search and URL-to-markdown readi
 packageName: "mcp-searxng"
 transport: STDIO
 repositoryUrl: https://github.com/ihor-sokoliuk/mcp-searxng
+# Readiness reads SearXNG's /config, which proves the instance answers without
+# fanning out to its engines. A searxng_web_search probe is a real search every
+# interval (1,440/day at 60s): it burns API-key engines (braveapi, kagi) and
+# feeds the IP blocks scraping engines put on the instance.
 healthCheck:
-  tool: searxng_web_search
-  arguments:
-    query: "mcp"
+  tool: searxng_instance_info
 env:
   - name: SEARXNG_URL
     description: >-