> ## 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.

# Tools and skills

> Enable and configure tools per agent: parameter bindings, sub-agents, and skills toggles.

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="agents (write)" />

## Tools vs. skills

IMP distinguishes two kinds of agent capability:

* **Tools** are server-side integrations — API calls, search functions, code runners, and data connectors — installed and managed by administrators. Each tool has a type, a category, and optionally a set of parameters that must be bound before the agent can use it.
* **Skills** are reusable prompt-level capabilities: pre-written reasoning patterns, formatting rules, or multi-step response strategies. Skills are toggled on per agent and do not require parameter configuration.

## The Tools & skills section

In the [workbench](/building/agents/workbench), open the **Tools & skills** section. The toolbar has:

* **Search** — filter by name or description ("Search tools by name or description…").
* **Category filter** — narrow to a single category (default "All categories"). Only categories present on this deployment appear.
* **Clear filters** (×) — resets search and category together.
* **Expand all / Collapse all** — open or close every category accordion.
* **Result count** — "`{n}` tool(s) found" when a filter is active, "`{n}` tool(s) available" when showing all.

Tools are grouped by category in an accordion. Each tool row shows the tool name, description, and an enable toggle.

## Enabling a tool

Toggle the switch on a tool row to enable it for this agent. For tools with required parameters, IMP automatically opens the **Configuration** sheet the moment you enable the tool so you can fill in the bindings immediately — the tool stays enabled even if you close the sheet before configuring, but it won't work until all required parameters have values.

<Note>
  A tool that has required parameters but no bindings set will not function at runtime. Check the configuration sheet for any tool the agent uses that produces unexpected errors.
</Note>

## Per-tool configuration

Many tools expose one or more parameters that must be bound to a value before the agent can call them. Parameter types include plain strings, numbers, and **variable references** — a dropdown that lets you pick a named variable from the organization's Variables store instead of hard-coding a value. Using variable references keeps secrets out of the agent form and allows administrators to rotate values in one place.

To configure a tool:

<Steps>
  <Step title="Enable the tool">
    Toggle the tool on in the Tools & skills section. If the tool has parameters, the configuration sheet opens automatically.
  </Step>

  <Step title="Fill in each parameter">
    For each parameter, either type a literal value or select a variable reference from the dropdown. The parameter's description tells you what the tool expects.
  </Step>

  <Step title="Close the sheet">
    Close the sheet. The configuration is staged locally until you save the agent.
  </Step>

  <Step title="Save the agent">
    Click **Save** in the workbench header or Save Bar.
  </Step>
</Steps>

You can reopen the configuration sheet at any time by clicking the **Configure** button (gear icon) on an already-enabled tool row.

## Sub-agents as tools

When **sub-agent orchestration** is enabled on this deployment, other agents appear in the Tools & skills section under the **Agents** category. Enabling an agent-as-tool means the current agent can call the sub-agent during a conversation — for example, routing specialized questions to a domain expert agent.

A toggle at the top of the Agents category controls whether the current agent's own tools and sub-agents are shown in the list ("Show this agent's tools & sub-agents"). Self-referential loops are excluded automatically.

<Tip>
  Use sub-agents to decompose complex workflows: a general assistant can delegate to a coding agent, a data agent, or a support agent depending on what the user asks.
</Tip>

## Skills

Below the tools accordion, the **Skills** section lists available skills. Each skill row shows the skill name and description with a toggle. Skills have no parameters — enabling one activates it for all conversations this agent handles.

See [Skills](/building/skills/overview) in the Building section for how to define custom skills.

## Next steps

<Columns cols={2}>
  <Card title="Back to workbench" icon="settings" href="/building/agents/workbench">
    Review all nine workbench sections.
  </Card>

  <Card title="Access" icon="shield" href="/building/agents/access-and-safety">
    Share the agent with users, roles, and teams.
  </Card>
</Columns>