DEV Community

Cover image for I Gave My Agent 200 MCP Tools — It Cost 24,522 Tokens Before It Did Any Work

I Gave My Agent 200 MCP Tools — It Cost 24,522 Tokens Before It Did Any Work

AheadKit on November 16, 2026

On Friday I measured what a handful of MCP tools cost an agent before it does any work: 16 tools from a real file server, 4,204 tokens. Fifty tools...
Collapse
 
shansjl profile image
shansjl •

A data point from a real server, counted your way (cl100k, compact JSON). Disclosure: I maintain CutVoke, an open-source video editor that agents drive over MCP.

Its server lists 52 tools, which come to 7,958 tokens, about 153 per tool. That's heavier than your synthetic ones, partly because the descriptions are in Chinese. Your whitespace point holds too: the same 52 pretty-printed are 12,567.

The bigger number is what isn't on the menu. There are 110 edit commands, and their payload schemas together come to 35,965 tokens. Instead of 110 more tools they all go through one command_apply(type, payload), and the agent fetches the schema for the one command it needs with commands_list(type=...) or editor_help(topic="command", command=...) right before using it. Even the name-only catalog (5,924 tokens) is fetched on demand rather than listed.

The trade-off: an unfamiliar command costs an extra round trip, and the model only sees a schema after it asks. An unknown command name comes back with an error pointing to commands_list. So your "let the agent ask for more" also works inside a single server, not only by splitting servers.

github.com/frankShan001/CutVoke

Collapse
 
aheadkit profile image
AheadKit •

This is the number I was missing — 153 a tool on a real server sits right between my lean synthetic ones and the filesystem server's 263, and the Chinese descriptions explain part of it. But the 35,965 hiding behind the lazy fetch is the part that got me: the menu looks cheap because the real schemas only show up when the agent asks. That trade-off's real too, an extra round trip every time the model meets a command it doesn't know. You basically built the version of 'let the agent ask for more' that lives inside one server instead of across several.

Collapse
 
shansjl profile image
shansjl •

Yes, that round trip is the part I keep weighing. Two things in the server try to make it land at the right moment: the MCP instructions tell the agent to call editor_help(topic='command', ...) or commands_list before an unfamiliar edit, so the lookup happens up front rather than after a failed call, and editor_help(topic='recipes') has worked examples with the payload shapes for common edits. It doesn't remove the extra call, it just makes it predictable. And yes, "let the agent ask for more", kept inside one server, is a fair way to put it.

Thread Thread
 
aheadkit profile image
AheadKit •

That's the version I'd actually trust — a lookup that happens up front, on purpose, costs less than one that happens after a failed call, and the worked examples mean the agent isn't guessing the payload shape mid-edit. Still an extra call either way, just one you can budget for instead of one that surprises you. 'Let the agent ask for more' is a fair way to put it, as long as it's one server asking, not five.

Thread Thread
 
mike-johnstone profile image
Mike Johnstone •

I'd compare them on completed editing tasks too: full schemas versus lazy lookup, same tasks and model. Then count successful edits, total tokens and latency, including retries. An extra lookup could pay for itself if it avoids wrong calls; the size of the tool list alone doesn't tell us that.

Thread Thread
 
aheadkit profile image
AheadKit •

That's the test that actually settles it — the list size never will. Same tasks, same model, full schemas against lazy lookup, and count what matters: edits that land, tokens, time with the retries in. I'll run that one.

Collapse
 
aryan_bulandi_4f767baf4a9 profile image
Aryan Bulandi •

That does make a noticeable difference between 122 tokens and 262 tokens for each tool. I thought it was an interesting point you made about descriptions increasing cost. Have you tried loading in tool definitions only when needed by an agent?

Collapse
 
aheadkit profile image
AheadKit •

Not yet — everything in this one was loaded up front, that's what the numbers are measuring. The lazy version is the next run, and there's a thread just below working out how to measure it fairly.

Collapse
 
paul_irolla_6b5ae261d0224 profile image
Paul Irolla •

Completed tasks is the test that settles it. The schema goes back over the wire on every turn, so its cost is its size times the number of turns run. I measure that on THOL: cost per solved task, checked by a verifier. (I built Tokenade.)

Collapse
 
aheadkit profile image
AheadKit •

Fair — 24,522 is the per-message number, and the bill that matters is that times however many turns a task actually takes. I haven't measured cost per solved task yet, that's the hole in this piece, so I'm going to run that one — same tasks, trimmed tool list, see what the per-task bill actually looks like. What kind of turns-per-task are you seeing on THOL with a list this size?

Collapse
 
paul_irolla_6b5ae261d0224 profile image
Paul Irolla •

@aheadkit Turns set the bill, so THOL ranks tools by cost per solved task. Every run records its turn count next to its cost, and the raw per-run results are published with the leaderboard. I'd rather point you there than quote a turns figure for a list this size.

Collapse
 
aheadkit profile image
AheadKit •

Fair enough, the leaderboard's the number then. Do the per-run rows break out by list size, or does a 200-tool run sit in the same ranking as a 20-tool one?