THE WORLD IS NOT STANDING STILL.RSS
BIG CHANGE.
BIG CHANGE, one tap away
BIG CHANGE, one tap away

Make room for the big picture.

Add BIG CHANGE to your home screen or desktop. It opens in its own window, with the latest stories when you’re online.

iPhone & iPad
Open bigchange.ai in Safari. Tap Share, then Add to Home Screen. Turn on Open as Web App if shown, then tap Add.
Android
Open bigchange.ai in Chrome. In the browser menu, choose Install app or Add to Home screen.
Desktop
In Chrome or Edge, use the install icon in the address bar or the browser’s app menu. In Safari on Mac, choose File → Add to Dock.

Markdown edition

# Correct tool calls can mislead agents and verifiers

> Correct tool results can lose limits in their text. Structured contracts expose missing fields; factual checks remain separate.

By BIGCHANGE.AI Editorial

Published: 2026-10-27T03:00:39.384Z
Updated: 2026-10-27T03:00:39.384Z
Canonical: https://bigchange.ai/blog/tool-output-wording-agents-verifiers-study

![Conceptual retrieval tray before deep archive shelves.](https://bigchange.ai/api/media/file/archive-result-limit-hero-v1.png)
AI-generated, BIG CHANGE.

In [*Who Verifies the Tools?*](https://arxiv.org/html/2610.32110v1), William Jeffries reports 20 retrieved documents from 4,772 matches, with the cap omitted.

## The big change

- **What changed:** Paired tool wording changed how identical results were interpreted.
- **Why it matters:** Tool protocols let builders expose boundaries in structured results and compare them with the text delivered to an agent or verifier. A shared text view cannot supply fields it omitted.
- **What to watch:** An output schema can require an identifier type. Validating that field's presence and form still leaves the actual record reference to check against its owning system.

## Where the information went missing

Four omissions involved search limits, result caps, page estimates and document-versus-scan IDs. The estimate was reconstructed from an unreleased draft.

## What the experiment found

Forty cases had eight pilots and 32 holdouts. Three models, five repeats and two wordings yielded 1,200 runs including pilots. For scope, completeness and uncertainty, fixed false answers flipped all 90 verifier judgments from acceptance to rejection. Under clear wording, 113/120 identifier **agent answers** still overclaimed. That wording bundled disclosures and instructions, so their effects remain inseparable.

## What a tool contract can check

The [Model Context Protocol tool specification](https://modelcontextprotocol.io/specification/2026-07-28/server/tools) separates a tool result's ordinary `content` from optional JSON `structuredContent`. A tool may declare an `outputSchema`. When it does, the server must return conforming structured content, and the client should validate it. The specification also recommends a text rendering of structured content for compatibility. A builder therefore has two surfaces to compare: the machine-readable value and the words the model may see.

[JSON Schema's object reference](https://json-schema.org/understanding-json-schema/reference/object#required) makes an important distinction. Listing a property under `properties` describes how to validate it *if present*; absence remains valid by default. The `required` keyword makes its presence mandatory, while `type` constrains the value's form. A proposed contract could require `resultLimit`, `totalKnown`, `isEstimated` and `idNamespace` fields. A missing field could fail validation before it is turned into prose.

Presence is only the first check. A numeric total can still be inaccurate, and a well-typed identifier can still point to the wrong record. Checking those values against the search implementation or owning data store is a separate operation. This is a contract design inference from the standards, not a tested repair in the archive study or a BIG CHANGE experiment.

One archive and a one-answer harness cannot establish general failure rates.

## Sources & further reading

- [Study](https://arxiv.org/html/2610.32110v1): methods.
- [Artifacts](https://github.com/williamcodes/who-verifies-the-tools): runs.
- [MCP specification](https://modelcontextprotocol.io/specification/2026-07-28/server/tools): structured tool results and output schemas.
- [JSON Schema](https://json-schema.org/understanding-json-schema/reference/object#required): required fields and type checks.

## Sources

- [Who Verifies the Tools?](https://arxiv.org/html/2610.32110v1) — Methods and limits.
- [Research artifacts](https://github.com/williamcodes/who-verifies-the-tools) — Frozen runs.
- [MCP tool specification](https://modelcontextprotocol.io/specification/2026-07-28/server/tools) — Structured results and output schema contract.
- [JSON Schema object reference](https://json-schema.org/understanding-json-schema/reference/object#required) — Required properties and type checks.