What’s the best way to prevent the input context from compounding with each tool call?
Claude Advanced Tool Use
11–20 of 280 posts
Re: Claude Advanced Tool Use
#12We 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 idea…
Well, what are those projects? I don't speak for anyone else, but I'm generally fatigued by the endless parade of science fair projects at this point, and operate under the assumption that if an approach is good enough, openai/anthropic/google will fold useful ideas under their tools/products.
Re: Claude Advanced Tool Use
#13> Tool Search Tool, which allows Claude to use search tools to access thousands of tools without consuming its context window
At some point, you run into the problem of having many tools that can accomplish the same task. Then you need a tool search engine, which helps you find the most relevant tool for your search keywords. But tool makers start to abuse Tool Engine Optimization (TEO) techniques to push their tools to the top of the tool rankings
Re: Claude Advanced Tool Use
#14Okay so this is just the `apropos` and `whatis` command¥ to search through available man pages. Then `man` command to discover how the tools work. Followed by tool execution?
Really. We should be treating Claude code more like a shell session. No need for MCPs
Re: Claude Advanced Tool Use
#15I am extremely excited to use programmatic tool use. This has, to date, been the most frustrating aspect of MCP-style tools for me: if some analysis requires the LLM to first fetch data and then write code to analyze it, the LLM is forced to manually copy a representation of the data into its interpreter.
Programmatic tool use feels like the way it always should have worked, and where agents seem to be going more broadly: acting within sandboxed VMs with a mix of custom code and programmatic interfaces to external services. This is a clear improvement over the LangChain-style Rupe Goldberg machines that we dealt with last year.
Re: Claude Advanced Tool Use
#16I see the pendulum has finished its swing from
> I HAVE NO TOOLS BECAUSE I’VE DESTROYED MY TOOLS WITH MY TOOLS.[1]
to
> TOOL SEARCH TOOL, WHICH ALLOWS CLAUDE TO USE SEARCH TOOLS TO ACCESS THOUSANDS OF TOOLS
---
[1] https://www.usenix.org/system/files/1311_05-08_mickens.pdf
Re: Claude Advanced Tool Use
#17So essentially all Claude users are going to surface the "coding agent", making it more suitable even for generic-purpose agents. That makes sense right after their blog post explaining the context bloating for MCPs.
I have been trying a similar idea that takes your MCP configs and runs WASM JavaScript in case you're building a browser-based agent: https://github.com/buremba/1mcp
Re: Claude Advanced Tool Use
#18We 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
I don't think any of the mainstream vendor APIs require MCP for tool use - they all supported functions (generally defined using a chunk of OpenAPI JSON schema) before the MCP spec gained widespread acceptance and continue to do so today.
Re: Claude Advanced Tool Use
#19> Tool Search Tool, which allows Claude to use search tools to access thousands of tools without consuming its context window At some point, you run into the problem of having many tools that can accomplish the same task. Then you need a tool search engine, which helps you find the most relevant tool for your search keywords. But tool makers start to abuse Tool Engine Optimization (TEO) techniques to push their tools…
Don't give anyone any ideas. We now have SEO, GEO, AEO and now TEO? :-p
Re: Claude Advanced Tool Use
#20[dead]