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
 
izgorodin profile image
Edward Izgorodin •

The menu is the one part of the window that is the same size on every message, which is also why it caches well. What grows is what the tools send back. I built the message list for 40 turns of a small triage agent whose only tool returns five GitHub issues as raw REST JSON, and counted it with o200k_base: at turn 20 the tool results were 99.1 percent of the tokens sent, about 326,000 tokens, more than thirteen times your 200-tool menu. Keeping only the last six turns flattened the call at about 99,000, because each result was 11,000 to 22,000 tokens on its own. Trimming each result to the five fields the agent reads kept the whole history and ended turn 40 at 36,934.

For the cost-per-solved-task run in this thread I would count three things separately: the definitions, the tool results, and the rest. A shorter tool list and a lazy schema lookup both shrink the first, and in a task with a few large reads the second is the one that decides the size of the window by the middle of the task.

Collapse
 
aheadkit profile image
AheadKit •

That flips the whole thread — the menu is the flat part, the results are what actually grows the window. 326,000 tokens at turn 20 against a 24,522 menu, that's not a rounding error, that's the bill. The trim to five fields is the run I want to steal, same tasks with full results against trimmed, see if the solved rate holds. Did the agent ever miss something it needed after you trimmed, or were the five fields everything it actually reads?

Collapse
 
izgorodin profile image
Edward Izgorodin •

The replay cannot tell you that: it called no model and used a fixed answer, so it measured how big the window gets, not whether the agent still finds what it needs. The five fields were the issue number, the title, the labels, the comment count and the first 300 characters of the body, which is what a triage prompt that cites numbers and suggests one existing label reads.

In your run with full against trimmed results, one cheap signal of a miss is a second fetch of the same issue within a task. Counting those per arm next to the solved rate would show whether the trim cut something the agent went back for.

Thread Thread
 
aheadkit profile image
AheadKit •

Fair catch on the replay — it proves the window shrinks, not that the agent still finds what it needs. The five fields make sense for a triage prompt that reads numbers and suggests one label, that's a clean cut. And I'm stealing the re-fetch signal — counting second fetches per arm next to the solved rate is the cheapest way to see if the trim cost anything. Did you land on five fields by trying fewer first, or was that the first cut that felt right?

Thread Thread
 
izgorodin profile image
Edward Izgorodin •

It was the first cut, taken from the prompt rather than found by trying fewer. The prompt asks the agent to cite issue numbers and suggest one existing label, so the number, the title and the labels had to stay, and the comment count and the first 300 characters of the body were the smallest context that still says what an issue is about. I did not test fewer fields. If you want the floor, drop one field at a time in the trimmed arm and watch the second-fetch count: a field the agent needs should show up there before it shows up in the solved rate.

Thread Thread
 
aheadkit profile image
AheadKit •

First cut from the prompt, not found by trying fewer — honest answer, and it makes the floor test the interesting one. Going to run that one: drop a field at a time in the trimmed arm and watch the second-fetch count before the solved rate moves. Which field would you drop first — the comment count, or the 300 chars?

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 •

@aheadkit Not on the site itself: results.sqlite sits at the repo root, next to reproduce_tables.py. The site renders from docs/data/results.json, which holds every raw measurement, and reproduce_tables.py prints the exact tables it shows. Your cut by list size can start from either.

Collapse
 
aheadkit profile image
AheadKit •

Found it — results.json is the easier start for the cut, thanks. Did reproduce_tables.py need anything beyond the sqlite file to run, or is it self-contained?

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?

Collapse
 
paul_irolla_6b5ae261d0224 profile image
Paul Irolla •

@aheadkit Not by list size. Each run is one row in the published results.sqlite (cost, token split, turns, duration), and the site groups them by session size, not by tool count. The raw file is there if you want to slice it yourself.

Collapse
 
aheadkit profile image
AheadKit •

Got it — session size, not tool count. The raw sqlite is the bit I actually need then, I'll slice it by list size myself and see where the 200-tool runs land. Is the file linked straight off the leaderboard page, or tucked away somewhere?

Collapse
 
kevinhall profile image
Kevin Hall •

what surprised me measuring real hosted tools was that the heaviest definition was almost all an output schema the server made up from past runs, nothing the author wrote. so the cost is not always in the descriptions

Collapse
 
aheadkit profile image
AheadKit •

That's a wrinkle my run never split out — my heaviest synthetic tool was 155 tokens and the real file server topped out at 408, but both were description plus input schema, I never weighed the output schema on its own. If the server generates it from past runs, trimming descriptions won't touch the biggest chunk, which flips my 'descriptions cost money' line a bit. Going to measure a real hosted server's definition split and see how much of the bill anyone actually wrote. How big was that generated output schema next to the description in your case?