fix: trim patterns response tokens and add missing documentation (#683)

- Trim task-specific patterns ~64%: drop displayName, shorten field names
  (frequency→freq), cap chains at 5, use short node type names in chains
- Add patterns mode to tools_documentation essentials, full docs, and
  tools-documentation.ts overview (was completely missing)
- Document includeOperations omission behavior for trigger/freeform nodes
- Add patterns return shape to search_templates returns documentation
- Trim search_nodes examples from 11 to 6

Conceived by Romuald Członkowski - https://www.aiadvisors.pl/en

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/mcp/tool-docs/discovery/search-nodes.ts

@@ -26,21 +26,16 @@ export const searchNodesDoc: ToolDocumentation = {
       mode: { type: 'string', description: 'Search mode: "OR" (any word matches, default), "AND" (all words required), "FUZZY" (typo-tolerant)', required: false },
       source: { type: 'string', description: 'Filter by node source: "all" (default, everything), "core" (n8n base nodes only), "community" (community nodes only), "verified" (verified community nodes only)', required: false },
       includeExamples: { type: 'boolean', description: 'Include top 2 real-world configuration examples from popular templates for each node. Default: false. Adds ~200-400 tokens per node.', required: false },
-      includeOperations: { type: 'boolean', description: 'Include resource/operation tree per node. Default: false. Adds ~100-300 tokens per result but saves a get_node round-trip.', required: false }
+      includeOperations: { type: 'boolean', description: 'Include resource/operation tree per node. Default: false. Adds ~100-300 tokens per result but saves a get_node round-trip. Only returned for nodes with resource/operation patterns — trigger nodes and freeform nodes (Code, HTTP Request) omit this field.', required: false }
     },
     returns: 'Array of node objects sorted by relevance score. Each object contains: nodeType, displayName, description, category, relevance score. For community nodes, also includes: isCommunity (boolean), isVerified (boolean), authorName (string), npmDownloads (number). Common nodes appear first when relevance is similar.',
     examples: [
       'search_nodes({query: "webhook"}) - Returns Webhook node as top result',
-      'search_nodes({query: "database"}) - Returns MySQL, Postgres, MongoDB, Redis, etc.',
       'search_nodes({query: "google sheets", mode: "AND"}) - Requires both words',
       'search_nodes({query: "slak", mode: "FUZZY"}) - Finds Slack despite typo',
-      'search_nodes({query: "http api"}) - Finds HTTP Request, GraphQL, REST nodes',
-      'search_nodes({query: "transform data"}) - Finds Set, Code, Function, Item Lists nodes',
       'search_nodes({query: "scraping", source: "community"}) - Find community scraping nodes',
-      'search_nodes({query: "pdf", source: "verified"}) - Find verified community PDF nodes',
-      'search_nodes({query: "brightdata"}) - Find BrightData community node',
       'search_nodes({query: "slack", includeExamples: true}) - Get Slack with template examples',
-      'search_nodes({query: "slack", includeOperations: true}) - Get Slack with resource/operation tree'
+      'search_nodes({query: "slack", includeOperations: true}) - Get Slack with resource/operation tree (7 resources, 44 ops)'
     ],
     useCases: [
       'Finding nodes when you know partial names',