Claude Advanced Tool Use
anthropic.com
Claude Advanced Tool Use
1–10 of 280 posts
Re: Claude Advanced Tool Use
#2We seem to be on a cycle of complexity -> simplicity -> complexity with AI agent design. First we had agents like Manus or Devin that had massive scaffolding around them, then we had simple LLMs in loops, then MCP added capabilities at the cost of context consumption, then in the last month everything has been bash + filesystem, and now we're back to creating more complex tools.
I wonder if there will be another round of simplifications as models continue to improve, or if the scaffolding is here to stay.
Re: Claude Advanced Tool Use
#3Tools for tools. How about an LLM tool for tools?
Re: Claude Advanced Tool Use
#4We seem to be on a cycle of complexity -> simplicity -> complexity with AI agent design. First we had agents like Manus or Devin that had massive scaffolding around them, then we had simple LLMs in loops, then MCP added capabilities at the cost of context consumption, then in the last month everything has been bash + filesystem, and now we're back to creating more complex tools. I wonder if there will be another roun…
Most of the time people sit on complex because they don't have a strong enough incentive to move from something that appears/happen to work, with AI, cost would be a huge incentive.
Re: Claude Advanced Tool Use
#5Nice! Feature #2 here is basically an implementation of the “write code to call tools instead of calling them directly” that was a big topic of conversation recently.
It uses their Python sandbox, is available via API, and exposes the tool calls themselves as normal tool calls to the API client - should be really simple to use!
Batch tool calling has been a game-changer for the AI assistant we've built into our product recently, and this sounds like a further evolution of this, really (primarily, it's about speed; if you can accomplish 2x more tools calls in one turn, it will usually mean your agent is now 2x faster).
Re: Claude Advanced Tool Use
#6I cannot believe all these months and years people have been loading all of the tool JSON schemas upfront. This is such a waste of context window and something that was already solved three years ago.
Re: Claude Advanced Tool Use
#7We seem to be on a cycle of complexity -> simplicity -> complexity with AI agent design. First we had agents like Manus or Devin that had massive scaffolding around them, then we had simple LLMs in loops, then MCP added capabilities at the cost of context consumption, then in the last month everything has been bash + filesystem, and now we're back to creating more complex tools. I wonder if there will be another roun…
This is what I've been talking about for a few months now. the AI field seems to reinvent the wheel every few months. And because most people really don't know what they're talking about, they just jump on the hype and adopt the new so-called standards without really thinking if it's the right approach. It really annoys me because I have been following some open source projects that have had some genuinely novel ideas about AI agent design. And they are mostly ignored by the community. But as soon as a large company like Anthropic or OpenAI starts a trend, suddenly everyone adopts it.
Re: Claude Advanced Tool Use
#8I'm confused about these tools - is this a decorator that you can add to your MCP server tools so that they don't pollute the context? How else would I add a "tool" for claude to use?
Re: Claude Advanced Tool Use
#9We seem to be on a cycle of complexity -> simplicity -> complexity with AI agent design. First we had agents like Manus or Devin that had massive scaffolding around them, then we had simple LLMs in loops, then MCP added capabilities at the cost of context consumption, then in the last month everything has been bash + filesystem, and now we're back to creating more complex tools. I wonder if there will be another roun…
Hmm the Gemini API doesn’t need MCP for tool-use if I understand correctly. It just needs registered functions
Re: Claude Advanced Tool Use
#10I'm confused about these tools - is this a decorator that you can add to your MCP server tools so that they don't pollute the context? How else would I add a "tool" for claude to use?
When you make API calls to generate chat completions, you specify a list of tools. They can be MCP tools, or just arbitrary tool metadata.
The API will then respond when it needs the client code to compute a tool output.