> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bizzyco.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Tool Permissions
> Allow, ask, or deny each tool an agent can call
Agents can use Bizzy tools — things like "read contact," "send email," "create
task." You control what each agent is allowed to do on a per-tool basis.
## The three permission levels
Each tool on each agent is set to one of three values:
| Level | Icon | Behavior |
| --------- | ------------- | ------------------------------------------------------ |
| **Allow** | Green check | Agent calls the tool silently — no interruption |
| **Ask** | Blue question | Agent pauses and requests your approval before calling |
| **Deny** | Red X | Tool is hidden from the agent entirely |
The "Ask" approval appears inline in the chat with a risk-level badge, and you
can expand the card to see the exact tool input before approving. A pending
approval waits as long as you need — there's no countdown or auto-deny — and the
agent can't continue that conversation until you allow or deny it (only one
approval is pending at a time). Allowing resumes the agent right where it
paused; denying lets it explain and carry on. Starting a new chat cancels a
pending approval.
## Finding the permissions UI
1. Open the agent's detail page.
2. Go to the **Tools** tab.
3. Tools are grouped by category (for example, Contacts, Messages, Tasks).
Expand a category to see its tools, each with a three-way button.
## How defaults work
When you create an agent, it inherits the **regular-user** baseline permissions
for the organization. Tools considered sensitive default to **Ask**; lower-risk
tools default to **Allow**.
Your overrides are stored sparsely — only the tools where you deviate from the
default are persisted. If the default shifts later (for example, we promote a
new tool from risky to routine), agents inherit the new default unless you had
explicitly overridden that tool.
## Risk levels
Tool approval cards display a risk badge (low / medium / high) to help you
decide quickly. Use your judgment: a low-risk tool misused is rarely damaging, a
high-risk tool might send email from your domain or spend money.
Changing permissions takes effect on the **next** tool call by the agent. A
tool call already mid-flight when you change the setting will complete under
the old rules.
## Next steps
See approvals in action
Review past approvals and denials