AgentTools.<tool>(tool_name="...", ...) or agent.add_tool.<tool>(tool_name="...", ...). Every tool requires a unique tool_name=. Each entry lists the tool’s configuration parameters. See the Agent reference for attaching and running tools.
api — API
Make an API request to a given URL.
Platform docs: API
bool
required
Whether to return the raw JSON response from the API
str
required
Target URL for the API Request
list[Dict[str, Any]]
The body parameters to include in the API request
list[Dict[str, Any]]
Files to include in the API request
list[Dict[str, Any]]
Headers to include in the API request
str
Choose the API Method desired (GET, POST, PUT, DELETE, PATCH)
list[Dict[str, Any]]
Query parameters to include in the API request
str
The raw JSON request to the API
arxiv — Arxiv Loader
Query ARXIV to return relevant articles
Platform docs: Arxiv Loader
bool
required
Whether to chunk the text
str
required
The ARXIV query
int
The overlap of the chunks
int
The size of the chunks to create
crunchbase — Crunchbase
Call the Crunchbase API to look up companies, people, funding rounds, and acquisitions.
Platform docs: Crunchbase
Any
JSON body for searches/* endpoints. IMPORTANT: categories and location_identifiers require UUIDs from autocomplete, not text! Example: {“field_ids”:[“identifier”,“funding_total”],“query”:[{“type”:“predicate”,“field_id”:“categories”,“operator_id”:“includes”,“values”:[“uuid-from-autocomplete”]}],“limit”:25}
Any
API path: ‘autocompletes’ | ‘entities/organizations/{id}’ | ‘entities/people/{id}’ | ‘searches/organizations’ | ‘searches/funding_rounds’ | ‘searches/people’
Any
Query string for GET requests. Autocomplete: ‘query={name}&collection_ids=organization.companies’. Entity lookup: ‘field_ids=short_description,funding_total&card_ids=founders’
exa_ai — Exa AI Search
Query the Exa search API
Platform docs: Exa AI Search
Any
Only return results crawled before this date (ISO 8601)
Any
Only return results published before this date (ISO 8601, e.g. 2024-12-31T00:00:00.000Z)
Any
Enable live crawling to fetch fresh content. When on, always fetches live content. When off, uses cached content.
str
default:"'EXA_AI_SEARCH'"
Select the search category to match the user’s query intent. Default to EXA_AI_SEARCH: General web search. Use general search for weather
int
default:"2000"
Maximum characters per result for text or highlights content
int
default:"10"
Number of results to return (1-100) default 10
str
default:"''"
The search query
Any
Search method: auto (default) intelligently combines methods, neural uses embeddings, fast is streamlined, instant is lowest latency, deep/deep-reasoning/deep-max offer increasing search depth, Generally default to auto
Any
Only return results crawled after this date (ISO 8601)
Any
Only return results published after this date (ISO 8601, e.g. 2024-01-01T00:00:00.000Z)
bool
default:"False"
Return LLM-selected highlights instead of full text. Uses ~10x fewer tokens with better relevance.
google_search — Google Search
Query the Google Search search API
Platform docs: Google Search
str
default:"'us'"
The location of the search
int
default:"10"
The number of results to return
str
default:"''"
The Google search query
str
default:"'web'"
Select the search type: Web, Image, Hotels, Events, or News
parallel_ai_search — Parallel Search
Search the web with Parallel’s Search API
Platform docs: Parallel Search
list[str]
default:"[]"
Exclude these domains from the response.
int
default:"1500"
Limit the excerpt length returned inside the excerpts object.
bool
default:"False"
Enable to fetch the latest version of each page instead of relying on cached index entries.
int
default:"1500"
Legacy field for truncating excerpts. Prefer the excerpts.* controls when available.
int
default:"10"
Upper bound on the number of results to return.
str
default:"'one-shot'"
Choose output presets. one-shot maximizes coverage, agentic optimizes for iterative agent loops.
str
default:"''"
Describe what the search should accomplish. Provide preferred sources or freshness hints here.
list[str]
default:"[]"
Prioritize these domains in ranked results.
str
default:"''"
Legacy tier selector. Leave blank to use the default tier for your workspace.
list[str]
default:"[]"
Optional structured keyword queries. At least one of objective or search queries is required.
perplexity_search — Perplexity Search
Query the Perplexity search API
Platform docs: Perplexity Search
str
default:"''"
Filter results last updated after this date
str
default:"''"
Filter results last updated before this date
int
default:"10"
The maximum number of results to return
Any
Maximum tokens per page
str
default:"''"
The search query
list[str]
default:"[]"
Additional queries to search for
bool
default:"False"
Whether to return images in results
bool
default:"True"
Whether to return snippets in results
str
default:"''"
Filter results published after this date
str
default:"''"
Filter results published before this date
list[str]
default:"[]"
Filter results to specific domains
str
default:"''"
The search mode to use
str
default:"''"
Filter results by recency
str
default:"''"
The latitude of the user’s location
str
default:"''"
The longitude of the user’s location
str
default:"''"
The name of the user’s location
str
default:"''"
The radius in kilometers for location-based search
url_loader — URL Scraper: Scrape URL
Scrape the contents from a URL
Platform docs: URL Scraper: Scrape URL
str
required
The provider to use for the URL Scraper
One of:
apify, jina, modalstr
required
The API key to use
str
required
The URL to load
bool
Whether to enhance the content
bool
Use a proxy to crawl the website
wikipedia — Get Wikipedia Article
Query Wikipedia to return relevant articles
Platform docs: Get Wikipedia Article
bool
required
Whether to chunk the text
str
required
The Wikipedia query
int
The overlap of the chunks
int
The size of the chunks to create
youtube — Get YouTube Transcript
Get the transcript of a youtube video.
Platform docs: Get YouTube Transcript
bool
required
Whether to chunk the text
str
required
The YouTube URL to get the transcript of
int
The overlap of the chunks
int
The size of the chunks to create