How many tokens is Claude Code's tool search actually saving you?

No - tool search is already on by default in current Claude Code for every model that supports it (Claude Sonnet 4.5, Haiku 4.5, Opus 4.5, and later). MCP tool schemas are deferred automatically; you don't flip a switch. What this tool estimates is the one setting still worth a look: ENABLE_TOOL_SEARCH=auto:N, which trades some of that saving back for skipping the search round-trip on servers small enough to fit under your chosen threshold.

With the default, every MCP schema is deferred no matter how small your setup is. With ENABLE_TOOL_SEARCH=auto:N, Claude Code instead loads the schemas it would otherwise defer straight into context as long as their combined size stays under N% of your context window, and only switches to full deferral once they cross it. Below the threshold you skip the extra tool-search lookup on first use; above it, you get the same deferred behavior as the default.

An estimate, built from the same curated per-server catalog the MCP Server Token Cost Checker uses - instruction-block size and full-schema size for well-known servers like GitHub, Playwright, and Supabase, with a conservative generic profile for anything else. Your real number depends on each server's actual current tool set, which only the free scan reads directly from your machine.

As an environment variable, or in the env block of your settings.json (see Claude Code's settings docs). It only takes effect on models that support tool search - Claude Sonnet 4.5, Haiku 4.5, Opus 4.5, and later - so on an older model the setting has no effect either way.

Yes. The scan and every fix are free - no card, no subscription, no signup. You only give an email if you want the optimization plan and one-command undo sent to your inbox.

The scan runs entirely on your machine. It never uploads your code, never reads your API key, and never sends your prompts or conversations anywhere. Only anonymous summary counts leave, and only if you choose to share them.

It reads your local setup and session history to find waste - idle MCP servers loaded into every session, an oversized CLAUDE.md re-sent on every request, duplicate file reads, and bloated tool output - then trims it losslessly, so each session carries less context and you hit your limit far less often.

ClockedCode is the curated, conflict-free Claude Code setup from the same maker. UsageCut makes your current setup leaner; ClockedCode makes it genuinely better - a set of hand-picked tools, specialist agents, and a tuned CLAUDE.md, installed in one paste.

Developers who use Claude Code daily and want a setup that is powerful out of the box instead of spending hours researching and wiring up plugins, agents, and MCP servers themselves.

A vetted, conflict-free bundle of hand-picked tools, specialist agents, and a tuned CLAUDE.md - everything installed together in one paste, with no setup archaeology.

Yes. ClockedCode is a one-time purchase with an instant download - no subscription and no recurring fees.

Yes. It installs alongside what you already have and is fully reversible. Run UsageCut first to clean your current setup, then add ClockedCode to level it up.