---
title: The 12,689-Token Typo: Why MCP Validation Errors Are So Big
description: A malformed ID on a production MCP tool returned a 12,689-token schema dump; the same mistake elsewhere cost 110–150. Why errors balloon, and the fix.
canonical: https://spiritroom.app/blog/verbose-validation-errors-tokens/
published: 2026-10-21
updated: 2026-10-21
---

> Markdown version of https://spiritroom.app/blog/verbose-validation-errors-tokens/ for agents. Index: /llms.txt

[Blog](/blog/) / [Tool results and errors](/guides/tool-results-and-errors-for-agents/)

# The 12,689-token typo: how one validation error can eat an agent's context

Agents make argument mistakes all the time: a wrong ID format, a label instead of an enum value, a date without a time. What your server sends back decides whether that costs 50 tokens or 12,000.

Leonid Bugaev · Published 21 Oct 2026

**TL;DR**

- **12,689 tokens** (47,623 bytes) for one malformed ID on an update tool, identical in 3 runs. It echoed the tool's entire input spec.
- **Same mistake, other tools:** 150 and 110 tokens. The size tracks the tool's schema, not the mistake.
- **On a mock:** a schema-dump error was 3,109 tokens; a one-line error with the fix was 51. Runs with an error went from 4/30 to 0/30 once the fixes were in.
- **Fix:** name the failing field, what was expected, what was got, and which tool returns a valid value. One line.
[What happened](#what)[Why errors balloon](#why)[Small versus large, on a mock](#mock)[The one-line error](#fix)[How we measured](#how-we-measured)[FAQ](#faq)

## What happened

We sent an update tool on a 99-tool production MCP server a malformed ID, a mistake agents make routinely. The server replied with the tool's entire input specification.

Update tool, malformed ID

*12,689 tokens (47,623 B)*

Feedback tool, bad enum

*150 tokens*

Get tool, bad ID

*110 tokens*

Identical in all 3 runs. Nowhere in it was a single line saying which field was wrong and what to send.

**Find your most expensive errors.**

We send fixed bad calls to every tool on your server and measure what each error costs agents, then show the one-line version.

[Audit your errors →](/#contact)

## Why errors balloon

- **Schema echo.** The validator prints everything it expected. The bigger the tool's schema, the bigger every error.
- **Type trees.** Another tool's error was a 15-line tree of internals (`readonly`, branded types) ending in `Expected "qualified", actual "to_review"`, three times.
- **It compounds.** The error stays in the conversation and is resent with every later request. See [MCP context window usage](/blog/mcp-context-window-usage/).

## Small versus large, on a mock

On a made-up task-tracker server we tried both error styles.

Schema-dump error

*3,109 tokens*

One-line error + fix

*51 tokens*

Runs with at least one error went from 4/30 (5–30%) to 0/30 (0–11%) with the fixed surface. That surface also accepted date-only input that used to fail, so the drop isn't from wording alone. Every errored run recovered either way: big errors cost tokens, not answers, here.

## The one-line error

```
Before: Invalid arguments: { readonly playId: ...; readonly expectedRevision: ...; ... 47 KB ... }
After:  playId "abc" is not an id. Use an id from list_plays. Nothing was changed.
```

- Field, expected, got, where to get a valid value.
- Say that nothing changed, so the agent retries instead of stopping.
- Don't tell the agent to ask the user about a typo. See [agent refusal states](/blog/agent-refusal-states/).
- Accept harmless variants (date-only, a screen label) instead of erroring. See [UI words vs API values](/blog/agent-vocabulary-mismatch/).

Full guide: [error messages for AI agents](/blog/error-messages-for-ai-agents/). Back to [tool results and errors for agents](/guides/tool-results-and-errors-for-agents/).

**Go deeper:** [Reduce tool response size](/blog/reduce-mcp-tool-response-size/), [How much MCP output is waste](/blog/mcp-context-pollution/), [MCP scorecard](/tools/mcp-scorecard/).

## How we measured

- **Live:** fixed bad calls sent directly to the production server, 3 identical runs, 16 Oct 2026, o200k\_base tokens.
- **Mock:** a made-up task tracker, 3 apps × 10 runs per surface, 21 Oct 2026; error sizes computed from the server directly. 95% Wilson ranges.
- **Limits:** one production server; the example field names are generalised.

## FAQ

### Why are MCP validation errors so large?

Many validation libraries print the whole expected schema, or a full type tree, when input doesn't match. For a tool with a big input schema, that's thousands of tokens. On the server we tested, one malformed ID returned 12,689 tokens.

### Does a big error hurt the agent?

It adds the whole error to the conversation, which is resent with every following request, and buries the cause. On the server we tested each such mistake added about 12.7k tokens.

### What should an MCP validation error contain?

The field, the expected value or format, what was sent, and where to get a valid value, in one line. For example: playId "abc" is not an id; use an id from list\_plays.

**Find your most expensive errors.**

We send fixed bad calls to every tool on your server and measure what each error costs agents, then show the one-line version.

[Audit your errors →](/#contact)

## Keep reading

- Up[Tool results and errors for AI agents (guide)](/guides/tool-results-and-errors-for-agents/)
- Related[How to write error messages for AI agents: before and after, from a production MCP server](/blog/error-messages-for-ai-agents/)
- Related[Why your MCP server fills the context window, and which agents actually pay for it](/blog/mcp-context-window-usage/)