{
  "id": 6354994,
  "title": "AI Agents - Tool Calling",
  "url": "https://urgent.news/2026/09/09/ai-agents-tool-calling",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-09T00:13:59.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/ramya_perumal/ai-agents-tool-calling-cie"
  },
  "original_language": "en",
  "account": "When a user requests the LLM to execute an action, such as obtaining the present weather or current stock market data, the LLM lacks the capability to acquire this information independently. To accomplish this, the LLM requires certain functionality or tools alongside a description of when to invoke these tools or functionality. The process unfolds as follows: The LLM scrutinizes the user's query to ascertain if it pertains to any of the outlined tools and their descriptions. If a match is found, the LLM proffers the suitable tool along with the pertinent parameters to the agent or external logic. Subsequently, the external logic carries out the designated action and transmits the outcome back to the LLM. The LLM examines the result and formulates the structured response. If the tool call is not identified, the LLM resorts to utilizing its internal knowledge to derive the answer. However, providing an ambiguous description may hinder the LLM from generating the desired output accurately. Consequently, the description for tool calls must be precise, enabling the LLM to semantically identify the tool and accurately match the arguments.",
  "summary": "When a user asks the LLM to perform an action, e.g., get the current weather or current stock market details, the LLM cannot get this information on its own. It needs some functionality or tools along with a description of when to call these tools/functionality. How is it working? The LLM analyzes the query to find out whether it is related to any of the tools and their descriptions. If so, the…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}