---
id: agent-tool-calls/2026-10
series: agent-tool-calls
title: Tools models call, October 2026
period: 2026-10
period_start: 2026-10-01
period_end: 2026-10-31
updated: 2026-11-11
license: CC BY 4.0
canonical: https://www.requesty.ai/data/agent-tool-calls/2026-10
latest: https://www.requesty.ai/data/agent-tool-calls
---

# Tools models call, October 2026

> 3.3% of chat requests in October 2026 returned at least one tool call. The most widely called tool name was "read", seen at 37.0% of organizations using tools.

Question: Which tools do LLMs call most often in production?

## Key findings

1. Top tool names by reach: "read" (37.0%), "bash" (33.0%), "edit" (30.6%), "write" (30.3%), "read_file" (23.6%).
2. "bash" appears in the most tool-call requests, 23.2% of them.
3. shell moved the most since September 2026: reach went from 5.1% to 11.6% (+6.4 pp).

## Data

| Tool name | Share of tool-using organizations | Share of tool-call requests | Organizations (band) |
| --- | --- | --- | --- |
| read | 36.96% | 8.94% | 100-499 |
| bash | 33.02% | 23.23% | 100-499 |
| edit | 30.57% | 3.08% | 100-499 |
| write | 30.30% | 1.42% | 100-499 |
| read_file | 23.64% | 1.38% | 100-499 |
| grep | 22.83% | 2.63% | 100-499 |
| glob | 21.88% | 0.89% | 100-499 |
| web_search | 20.92% | 1.93% | 100-499 |
| skill | 15.49% | 0.39% | 100-499 |
| write_file | 13.86% | 0.90% | 100-499 |
| terminal | 13.45% | 5.73% | 25-99 |
| webfetch | 12.77% | 0.10% | 25-99 |
| execute_code | 11.96% | 0.88% | 25-99 |
| search_files | 11.68% | 0.58% | 25-99 |
| shell | 11.55% | 1.46% | 25-99 |
| skill_view | 10.60% | 0.53% | 25-99 |
| patch | 10.33% | 0.75% | 25-99 |
| websearch | 10.19% | 0.07% | 25-99 |
| skill_manage | 9.10% | 0.34% | 25-99 |
| memory | 8.29% | 0.08% | 25-99 |
| tool_call | 8.02% | 0.35% | 25-99 |
| todowrite | 7.88% | 0.24% | 25-99 |
| question | 7.88% | 0.04% | 25-99 |
| skills_list | 7.74% | 0.04% | 25-99 |
| tool_search | 7.74% | 0.06% | 25-99 |
| execute | 7.20% | 0.20% | 25-99 |
| ask_user | 6.79% | 0.12% | 25-99 |
| web_fetch | 6.66% | 0.07% | 25-99 |
| web_extract | 6.39% | 0.05% | 25-99 |
| tool_describe | 6.25% | 0.05% | 25-99 |
| task | 5.98% | 0.30% | 25-99 |
| exec | 5.98% | 0.73% | 25-99 |
| apply_patch | 5.84% | 0.81% | 25-99 |
| search_web | 5.57% | 0.05% | 25-99 |
| ls | 5.16% | 0.27% | 25-99 |
| agent | 5.03% | 0.08% | 25-99 |
| list_files | 5.03% | 0.02% | 25-99 |
| fetch_url | 5.03% | 0.28% | 25-99 |
| vision_analyze | 4.76% | 0.08% | 25-99 |
| clarify | 4.76% | 0.01% | 25-99 |

## Method

- Tool names come from the tool calls in model responses, lowercased. A tool counts once per request even if it is called several times.
- A tool name needs 10 or more organizations before it is listed, on top of the standard floors, so names specific to one company never appear.
- Tool-call data is recorded from July 2026, so this series starts then.
- A row is published only when it has at least 20 requests, at least 5 distinct organizations, and no single organization above 80% of its traffic. These are the same floors /rankings uses. Rows below the floors are withheld, not estimated.
- Only shares, rates, medians and organization bands are published. Absolute request, token and spend totals stay private.

## Caveats

- Different agents name the same tool differently (read vs read_file, bash vs shell vs terminal). Names are not merged.
- Only tool calls the model returned are counted, not tools that were offered but unused.

## Cite as

Requesty (2026). Tools models call, October 2026. Requesty Data. https://www.requesty.ai/data/agent-tool-calls/2026-10

```bibtex
@misc{requesty_agent_tool_calls_2026_10,
  author       = {{Requesty}},
  title        = {Tools models call, October 2026},
  year         = {2026},
  howpublished = {\url{https://www.requesty.ai/data/agent-tool-calls/2026-10}},
  note         = {Requesty Data}
}
```

Source: Requesty production gateway. License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/).
Downloads: [JSON](https://www.requesty.ai/data/agent-tool-calls/2026-10/data.json) · [CSV](https://www.requesty.ai/data/agent-tool-calls/2026-10/data.csv) · [Markdown](https://www.requesty.ai/data/agent-tool-calls/2026-10/data.md)