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

# MCP Task Design

> Creating tasks for MCP tool-use environments

MCP tasks evaluate an agent's ability to use tools effectively—calling the right functions with correct parameters to accomplish goals across calendar, email, CRM, filesystem, and other services.

## Task Components

| Component       | Purpose                                         |
| --------------- | ----------------------------------------------- |
| `ENABLED_TOOLS` | Tools available to the model (constraint space) |
| `PROMPT`        | User's query                                    |
| `TRAJECTORY`    | Intended sequence of tool calls (ground truth)  |
| `GTFA_CLAIMS`   | Required factual claims in final response       |

***

## Component Details

### ENABLED\_TOOLS

Defines which tools the agent can access. Constraining tools increases task focus and reduces ambiguity.

```json theme={null}
{
  "ENABLED_TOOLS": [
    "calendar_get_events",
    "calendar_add_event",
    "email_send",
    "email_search"
  ]
}
```

**Considerations:**

* Include only tools relevant to the task
* Adding irrelevant tools tests discrimination ability

### PROMPT

The natural language instruction given to the agent.

```json theme={null}
{
  "PROMPT": "Schedule a meeting with Sarah for next Tuesday at 2pm and send her a calendar invite via email"
}
```

**Prompt Design Tips:**

* Be specific about expected outcomes
* Include implicit constraints (e.g., "during business hours")

### TRAJECTORY

The expected sequence of tool calls (ground truth). Used for trajectory-based evaluation.

```json theme={null}
{
  "TRAJECTORY": [
    {
      "tool": "calendar_add_event",
      "args": {
        "title": "Meeting with Sarah",
        "datetime": "2025-01-21T14:00:00",
        "attendees": ["sarah@example.com"]
      }
    },
    {
      "tool": "email_send",
      "args": {
        "to": "sarah@example.com",
        "subject": "Meeting Invitation",
        "body": "..."
      }
    }
  ]
}
```

**Note:** Trajectories represent one valid path—agents may complete tasks via different valid sequences.

### GTFA\_CLAIMS

Ground Truth Factual Assertions that must be present in the agent's final response.

```json theme={null}
{
  "GTFA_CLAIMS": [
    "Agent created a calendar event for Tuesday at 2:00 PM",
    "Event includes Sarah as an attendee",
    "Confirmation email was sent to sarah@example.com"
  ]
}
```

***

## Example Task Structure

### Complete Example

```json theme={null}
{
  "ENABLED_TOOLS": [
    "calendar_get_events",
    "calendar_add_event",
    "calendar_delete_event",
    "email_send",
    "contacts_search"
  ],
  "PROMPT": "Check my calendar for Friday. If I have a meeting with the marketing team, cancel it and send an apology email to all attendees.",
  "TRAJECTORY": [
    { "tool": "calendar_get_events", "args": { "date": "Friday" } },
    { "tool": "calendar_delete_event", "args": { "event_id": "mktg-123" } },
    { "tool": "email_send", "args": { "to": ["alice@co.com", "bob@co.com"], "subject": "Meeting Cancelled" } }
  ],
  "GTFA_CLAIMS": [
    "Agent checked Friday's calendar",
    "Agent identified the marketing team meeting",
    "Agent cancelled the meeting",
    "Agent sent apology email to all attendees (Alice and Bob)"
  ]
}
```

***

## Best Practices

<Accordion title="Define clear success criteria">
  GTFA claims should be specific and unambiguous:

  ❌ "Agent completed the task correctly"

  ✅ "Agent sent email to [john@example.com](mailto:john@example.com) with subject containing 'Q3 Report'"
</Accordion>

<Accordion title="Include boundary cases">
  Test agent behavior at the edges:

  * What if no results are found?
  * What if multiple matches exist?
  * What if required information is missing?
</Accordion>

<Accordion title="Balance tool availability">
  * Too few tools: Task may be impossible
  * Too many tools: Agent may get confused
  * Include 1-2 "distractor" tools to test discrimination
</Accordion>

<Accordion title="Design for multiple valid paths">
  Many tasks can be completed different ways. Ensure GTFA claims verify outcomes, not specific tool sequences.
</Accordion>

<Accordion title="Test with realistic data">
  Use data packs that reflect real usage patterns—realistic contact names, plausible email content, believable calendar schedules.
</Accordion>

***

## Next Steps

<CardGroup cols={2}>
  <Card title="MCP Verifiers" icon="check-circle" href="/deep-dives/verifiers/mcp">
    Configure LLM Judge and GTFA evaluation
  </Card>

  <Card title="Website Tasks" icon="globe" href="/deep-dives/task-design/website">
    Web application task design
  </Card>
</CardGroup>