traffic-webmcp.netlify.app WebMCP Tools, Schemas & Agent Capabilities

traffic-webmcp.netlify.app

demo Unverified (seed import) Productivity & Business 8 tools imperative implementation

A signalized intersection a human and an AI agent operate together. The simulation runs entirely in the tab and exposes eight WebMCP tools.

First seen 2026-09-14 · Last seen 2026-09-14 · Source: webmcp.com

Answer 2 · Act 6 · Transact 0 · Score: Not yet scored

Tool inspector

run_batch

act imperative

Evaluate up to 50 candidate signal timings headlessly and return the resulting metrics for each. Runs off the main thread; the live junction keeps running while this executes. Deterministic: identical (config, seed) pairs always produce identical metrics. Single-seed figures carry roughly ±2 s of noise on mean_wait_s, so average across at least 3 seeds before concluding that one timing beats another by a small margin. This tool reports physics, not policy: it evaluates timings that are illegal to deploy and tells you honestly how they perform. Each row carries an `admissible` flag and, when false, the constraints it violates — so you can see the fast illegal options without spending a search on them. Enforcement still belongs to apply_config. If `admissible_count` comes back much lower than the batch size, the region you are searching is mostly out of bounds. Read `constraints` in describe_model before continuing. Results are sorted by mean_wait_s ascending. The top 3 carry the full per-arm breakdown; the rest carry the summary metrics needed to rank them. Pass detail="full" if you need per-arm figures for every row.

Input schema

Property	Type	Required	Description
`configs`	array	yes	Candidate timings to evaluate.
`seeds`	array	no	Random seeds to average over. Defaults to [1,2,3].
`sim_minutes`	number	no	Simulated minutes per run after a 5-minute warm-up. Defaults to 20. Shorter runs are faster but noisier.
`scenario_id`	string	no	Demand scenario to evaluate against. Defaults to the active one. Evaluating against a scenario does not switch the live view.
`detail`	string	no	summary (default) gives full per-arm figures for the top 3 rows and summary metrics for the rest. full gives per-arm figures for every row, which for 50 configs is a large payload.

Raw JSON schema

{
  "type": "object",
  "properties": {
    "configs": {
      "type": "array",
      "minItems": 1,
      "maxItems": 50,
      "items": {
        "type": "object",
        "properties": {
          "ns_green_s": {
            "type": "number",
            "minimum": 7,
            "maximum": 90,
            "description": "North–south through green, seconds."
          },
          "ew_green_s": {
            "type": "number",
            "minimum": 7,
            "maximum": 90,
            "description": "East–west through green, seconds."
          },
          "yellow_s": {
            "type": "number",
            "minimum": 4,
            "maximum": 6,
            "description": "Yellow after every green, seconds. Safety-derived floor of 4 s — see the min_yellow constraint."
          },
          "all_red_s": {
            "type": "number",
            "minimum": 2,
            "maximum": 4,
            "description": "All-red clearance, seconds. Safety-derived floor of 2 s — see the min_all_red constraint."
          },
          "left_protected": {
            "type": "boolean",
            "description": "Give NS left turns an exclusive phase."
          },
          "ns_left_green_s": {
            "type": "number",
            "minimum": 0,
            "maximum": 30,
            "description": "Protected left phase duration. Must be 0 when left_protected is false."
          }
        },
        "required": [
          "ns_green_s",
          "ew_green_s",
          "yellow_s",
          "all_red_s",
          "left_protected",
          "ns_left_green_s"
        ],
        "additionalProperties": false
      },
      "description": "Candidate timings to evaluate."
    },
    "seeds": {
      "type": "array",
      "items": {
        "type": "integer"
      },
      "maxItems": 5,
      "description": "Random seeds to average over. Defaults to [1,2,3]."
    },
    "sim_minutes": {
      "type": "number",
      "minimum": 5,
      "maximum": 60,
      "description": "Simulated minutes per run after a 5-minute warm-up. Defaults to 20. Shorter runs are faster but noisier."
    },
    "scenario_id": {
      "type": "string",
      "description": "Demand scenario to evaluate against. Defaults to the active one. Evaluating against a scenario does not switch the live view."
    },
    "detail": {
      "type": "string",
      "enum": [
        "summary",
        "full"
      ],
      "description": "summary (default) gives full per-arm figures for the top 3 rows and summary metrics for the rest. full gives per-arm figures for every row, which for 50 configs is a large payload."
    }
  },
  "required": [
    "configs"
  ],
  "additionalProperties": false
}