fix(firecrawl): declare news and image result fields in the search output schema

Author: waleedlatif1

apps/docs/content/docs/integrations/firecrawl.mdx

@@ -156,14 +156,20 @@ Search for information on the web using Firecrawl
 | --------- | ---- | ----------- |
 | `data` | array | Search results data with scraped content and metadata |
 |   ↳ `title` | string | Search result title from search engine |
-|   ↳ `description` | string | Search result description/snippet from search engine |
+|   ↳ `description` | string | Search result description/snippet from search engine; web results only |
 |   ↳ `url` | string | URL of the search result |
+|   ↳ `snippet` | string | News result snippet; news results only |
+|   ↳ `date` | string | News publication date; news results only |
+|   ↳ `imageUrl` | string | Image URL; image results, and news results that carry one |
+|   ↳ `imageWidth` | number | Image width in pixels; image results only |
+|   ↳ `imageHeight` | number | Image height in pixels; image results only |
+|   ↳ `position` | number | Rank within its source; news and image results only |
 |   ↳ `markdown` | string | Page content in markdown; returned only when scraping was requested via the hidden scrapeOptions input |
 |   ↳ `html` | string | Processed HTML content; returned only when "html" is among the scrape formats requested via the hidden scrapeOptions input |
 |   ↳ `rawHtml` | string | Unprocessed raw HTML; returned only when "rawHtml" is among the scrape formats requested via the hidden scrapeOptions input |
 |   ↳ `links` | array | Links found on the page; returned only when "links" is among the scrape formats requested via the hidden scrapeOptions input |
 |   ↳ `screenshot` | string | Screenshot URL \(expires after 24 hours\); returned only when "screenshot" is among the scrape formats requested via the hidden scrapeOptions input |
-|   ↳ `metadata` | object | Metadata about the search result page |
+|   ↳ `metadata` | object | Metadata about the search result page; web and news results only |
 |     ↳ `title` | string | Page title |
 |     ↳ `description` | string | Page meta description |
 |     ↳ `sourceURL` | string | Original source URL |

apps/sim/tools/firecrawl/types.ts

@@ -120,7 +120,8 @@ export const SEARCH_METADATA_OUTPUT_PROPERTIES = {
  */
 export const SEARCH_METADATA_OUTPUT: OutputProperty = {
   type: 'object',
-  description: 'Metadata about the search result page',
+  description: 'Metadata about the search result page; web and news results only',
+  optional: true,
   properties: SEARCH_METADATA_OUTPUT_PROPERTIES,
 }
 
@@ -154,9 +155,36 @@ export const SEARCH_RESULT_OUTPUT_PROPERTIES = {
   title: { type: 'string', description: 'Search result title from search engine' },
   description: {
     type: 'string',
-    description: 'Search result description/snippet from search engine',
+    description: 'Search result description/snippet from search engine; web results only',
+    optional: true,
   },
   url: { type: 'string', description: 'URL of the search result' },
+  snippet: {
+    type: 'string',
+    description: 'News result snippet; news results only',
+    optional: true,
+  },
+  date: { type: 'string', description: 'News publication date; news results only', optional: true },
+  imageUrl: {
+    type: 'string',
+    description: 'Image URL; image results, and news results that carry one',
+    optional: true,
+  },
+  imageWidth: {
+    type: 'number',
+    description: 'Image width in pixels; image results only',
+    optional: true,
+  },
+  imageHeight: {
+    type: 'number',
+    description: 'Image height in pixels; image results only',
+    optional: true,
+  },
+  position: {
+    type: 'number',
+    description: 'Rank within its source; news and image results only',
+    optional: true,
+  },
   markdown: {
     type: 'string',
     description:
@@ -372,16 +400,23 @@ export interface ScrapeResponse extends ToolResponse {
 
 export interface SearchResponse extends ToolResponse {
   output: {
+    /** Web, then news, then image results; each source fills only its own fields. */
     data: Array<{
-      title: string
-      description: string
+      title?: string
+      description?: string
       url: string
+      snippet?: string
+      date?: string
+      imageUrl?: string
+      imageWidth?: number
+      imageHeight?: number
+      position?: number
       markdown?: string
       html?: string
       rawHtml?: string
       links?: string[]
       screenshot?: string
-      metadata: {
+      metadata?: {
         title?: string
         description?: string
         sourceURL: string