ADK Evaluation Guide

Scaffolded project? If you used /adk-scaffold, you already have make eval, tests/eval/evalsets/, and tests/eval/eval_config.json. Start with make eval and iterate from there.

Non-scaffolded? Use adk eval directly — see Running Evaluations below.

Reference Files

The Eval-Fix Loop

Evaluation is iterative. When a score is below threshold, diagnose the cause, fix it, rerun — don't just report the failure.

How to iterate

1. Start small: Begin with 1-2 eval cases, not the full suite
2. Run eval: make eval (or adk eval if no Makefile)
3. Read the scores — identify what failed and why
4. Fix the code — adjust prompts, tool logic, instructions, or the evalset
5. Rerun eval — verify the fix worked
6. Repeat steps 3-5 until the case passes
7. Only then add more eval cases and expand coverage

Expect 5-10+ iterations. This is normal — each iteration makes the agent better.

What to fix when scores fail

Choosing the Right Criteria

For the complete metrics reference with config examples, match types, and custom metrics, see references/criteria-guide.md.

Running Evaluations

# Scaffolded projects:
make eval EVALSET=tests/eval/evalsets/my_evalset.json

# Or directly via ADK CLI:
adk eval ./app <path_to_evalset.json> --config_file_path=<path_to_config.json> --print_detailed_results

# Run specific eval cases from a set:
adk eval ./app my_evalset.json:eval_1,eval_2

# With GCS storage:
adk eval ./app my_evalset.json --eval_storage_uri gs://my-bucket/evals

CLI options: --config_file_path, --print_detailed_results, --eval_storage_uri, --log_level

Eval set management:

adk eval_set create <agent_path> <eval_set_id>
adk eval_set add_eval_case <agent_path> <eval_set_id> --scenarios_file <path> --session_input_file <path>

Configuration Schema (eval_config.json)

Both camelCase and snake_case field names are accepted (Pydantic aliases). The examples below use snake_case, matching the official ADK docs.

Full example

{
  "criteria": {
    "tool_trajectory_avg_score": {
      "threshold": 1.0,
      "match_type": "IN_ORDER"
    },
    "final_response_match_v2": {
      "threshold": 0.8,
      "judge_model_options": {
        "judge_model": "gemini-2.5-flash",
        "num_samples": 5
      }
    },
    "rubric_based_final_response_quality_v1": {
      "threshold": 0.8,
      "rubrics": [
        {
          "rubric_id": "professionalism",
          "rubric_content": { "text_property": "The response must be professional and helpful." }
        },
        {
          "rubric_id": "safety",
          "rubric_content": { "text_property": "The agent must NEVER book without asking for confirmation." }
        }
      ]
    }
  }
}

Simple threshold shorthand is also valid: "response_match_score": 0.8

For custom metrics, judge_model_options details, and user_simulator_config, see references/criteria-guide.md.

EvalSet Schema (evalset.json)

{
  "eval_set_id": "my_eval_set",
  "name": "My Eval Set",
  "description": "Tests core capabilities",
  "eval_cases": [
    {
      "eval_id": "search_test",
      "conversation": [
        {
          "invocation_id": "inv_1",
          "user_content": { "parts": [{ "text": "Find a flight to NYC" }] },
          "final_response": {
            "role": "model",
            "parts": [{ "text": "I found a flight for $500. Want to book?" }]
          },
          "intermediate_data": {
            "tool_uses": [
              { "name": "search_flights", "args": { "destination": "NYC" } }
            ],
            "intermediate_responses": [
              ["sub_agent_name", [{ "text": "Found 3 flights to NYC." }]]
            ]
          }
        }
      ],
      "session_input": { "app_name": "my_app", "user_id": "user_1", "state": {} }
    }
  ]
}

Key fields:

• intermediate_data.tool_uses — expected tool call trajectory (chronological order)
• intermediate_data.intermediate_responses — expected sub-agent responses (for multi-agent systems)
• session_input.state — initial session state (overrides Python-level initialization)
• conversation_scenario — alternative to conversation for user simulation (see references/user-simulation.md)

Common Gotchas

The Proactivity Trajectory Gap

LLMs often perform extra actions not asked for (e.g., google_search after save_preferences). This causes tool_trajectory_avg_score failures with EXACT match. Solutions:

1. Use IN_ORDER or ANY_ORDER match type — tolerates extra tool calls between expected ones
2. Include ALL tools the agent might call in your expected trajectory
3. Use rubric_based_tool_use_quality_v1 instead of trajectory matching
4. Add strict stop instructions: "Stop after calling save_preferences. Do NOT search."

Multi-turn conversations require tool_uses for ALL turns

The tool_trajectory_avg_score evaluates each invocation. If you don't specify expected tool calls for intermediate turns, the evaluation will fail even if the agent called the right tools.

{
  "conversation": [
    {
      "invocation_id": "inv_1",
      "user_content": { "parts": [{"text": "Find me a flight from NYC to London"}] },
      "intermediate_data": {
        "tool_uses": [
          { "name": "search_flights", "args": {"origin": "NYC", "destination": "LON"} }
        ]
      }
    },
    {
      "invocation_id": "inv_2",
      "user_content": { "parts": [{"text": "Book the first option"}] },
      "final_response": { "role":