{
  "schema_version": 1,
  "status": "reported-local-result",
  "created_at": "2026-07-15",
  "benchmark": "algo-tool-context-efficiency-v1",
  "source_tag": "v0.17.0",
  "source_revision": "ee9abeb185081538bbe3b3a38545444f252cdeda",
  "command": "python -m algo_cli.evals.tool_context_efficiency",
  "repeats": 7,
  "catalog_tool_count": 56,
  "serialized_catalog_tool_count": 56,
  "full_schema_tokens": 7571,
  "coding_scenarios": [
    {
      "id": "code_repair",
      "label": "Code repair",
      "prompt": "Fix the failing parser and run tests, then verify the diff.",
      "required_tools": ["edit_file", "run_shell", "git_diff"],
      "selected_schema_tokens": 2029,
      "schema_tokens_saved": 5542,
      "schema_reduction_pct": 73.2,
      "missing_required_tools": [],
      "stable_across_repeats": true
    },
    {
      "id": "existing_file_update",
      "label": "Safe configuration update",
      "prompt": "Update the existing configuration file safely and verify it.",
      "required_tools": ["read_file", "edit_file", "run_shell", "git_diff"],
      "selected_schema_tokens": 1946,
      "schema_tokens_saved": 5625,
      "schema_reduction_pct": 74.297,
      "missing_required_tools": [],
      "stable_across_repeats": true
    }
  ],
  "all_scenarios": {
    "count": 9,
    "median_selected_schema_tokens": 1544,
    "median_schema_reduction_pct": 79.606,
    "minimum_schema_reduction_pct": 73.2,
    "required_tools_recalled": 19,
    "required_tools_total": 19
  },
  "required_tool_recall": 1.0,
  "semantic_supersession": {
    "before_tokens": 22525,
    "after_tokens": 4637,
    "tokens_saved": 17888,
    "reduction_pct": 79.414,
    "latest_result_preserved": true,
    "protocol_pairing_preserved": true,
    "idempotent": true
  },
  "typed_program": {
    "raw_intermediate_tokens": 7063,
    "compact_result_tokens": 196,
    "tokens_saved": 6867,
    "reduction_pct": 97.225,
    "correct_result": true,
    "artifact_backed": true,
    "receipt_chains_valid": true
  },
  "gates": {
    "minimum_repeats": 3,
    "minimum_median_schema_reduction_pct": 60.0,
    "minimum_scenario_schema_reduction_pct": 45.0,
    "minimum_supersession_reduction_pct": 75.0,
    "minimum_typed_program_reduction_pct": 70.0,
    "required_tool_recall": 1.0
  },
  "report_sha256": "00e5428d2f6ba08faac6dc6021a4950da8168b1c08f8c2efd90ff971f6c3dd25",
  "claim": "In two deterministic coding scenarios, Algo CLI used 73.2% to 74.3% fewer tool-schema tokens than exposing the full 56-tool catalog while recalling every required tool.",
  "limitations": "This deterministic, model-free harness benchmark measures estimated tool-schema and intermediate-result context. It does not measure model output tokens, end-to-end coding quality, provider billing, or superiority over another harness. Token estimates use a documented characters-divided-by-four approximation and results have not been independently reproduced."
}