> ## Documentation Index
> Fetch the complete documentation index at: https://docs.intelligence-management-platform.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Tool approvals

> Understand when IMP asks you to approve a tool call and what each option does.

export const RightsCallout = ({right, flags}) => <Info>
    Who sees this: requires {right === "none" ? "no special rights — available to every signed-in user" : `the ${right} right (or super admin)`}.
    {flags && flags !== "none" ? ` Only visible when the server enables ${flags}.` : ""}
  </Info>;

<RightsCallout right="none" flags="none" />

When the agent wants to run a tool, IMP pauses and shows you an approval card. You stay in control of what runs in your name.

<Frame caption="The tool approval card: the agent requests to run Email, you review the content, and choose Allow once — the agent proceeds and confirms the action.">
  <video autoPlay muted loop playsInline src="https://mintcdn.com/exulu/HUjjVgs8aB3PSMha/videos/approve-tool-call.mp4?fit=max&auto=format&n=HUjjVgs8aB3PSMha&q=85&s=34736b226ac4e7c570d31fe9496b8b27" data-path="videos/approve-tool-call.mp4" />
</Frame>

## Why tools need approval

Most tools require approval by default. This means every time the agent would call a tool, it asks first rather than running silently. You can see the tool name and a short preview of what it is about to do before you decide.

Some tools — such as the image generation widget and certain internal context tools — have approval turned off by default and run without prompting. The tools you see in a conversation depend on what the agent's administrator has enabled.

<Note>
  Tool parameters configured by an administrator are shown in the approval card for transparency, but you cannot edit them. Only the agent's administrator can change those settings.
</Note>

## The approval card

When the agent requests to run a tool, a card appears inline in the conversation:

**Run `{tool}`?**

"The agent wants to run this tool. Review the request and choose how to proceed."

Below the description, a monospace block previews the key input the tool will use (for example, a file path, a command, a URL, or a query). Three buttons follow:

| Button                  | What it does                                                                                                                         |
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------ |
| **Allow once**          | Runs the tool a single time. The next time the agent wants to call the same tool, you are asked again.                               |
| **Allow for this chat** | Runs the tool now and pre-approves it for the rest of this conversation. Future calls to the same tool proceed without another card. |
| **Deny**                | Blocks this specific call. The agent receives a denial response and may try a different approach or ask you to reconsider.           |

After you respond, the card collapses into a compact status line — "Approved: `{tool}`" or "Denied: `{tool}`" — so the conversation stays readable.

## Reviewing what you have already approved

Open **Skills & tools** from the **＋** menu in the composer. The **Approved for this chat** section lists every tool you have pre-approved in this conversation, with a **Revoke** button next to each one. Revoking a pre-approval means the agent will ask again the next time it wants to call that tool.

<Tip>
  Use **Allow for this chat** when you expect the agent to call the same tool several times in one task — for example, reading multiple files or running several searches in a row. Use **Allow once** when you want to stay in the loop on each step.
</Tip>

## Next steps

<Columns cols={2}>
  <Card title="Skills and tools" icon="wrench" href="/user-guide/chat/overview#the-add-to-conversation-menu">
    Enable or disable individual tools and skills for a conversation.
  </Card>

  <Card title="Context compaction" icon="archive" href="/user-guide/chat/context-compaction">
    Keep the conversation within the model's context window.
  </Card>
</Columns>