Skip to main content
Glama

HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, News

Predictive probability engine: regression, normal model, p-values

hubvibe_predictive_probability_engine
Read-onlyIdempotent

Predictive probability and regression engine: least-squares linear regression with standard errors, confidence and prediction intervals, a fitted normal distribution with quantiles and probability queries (P(y > t)), exact Student t and Jarque-Bera p-values. Points inline or from a BigQuery table. Deterministic arithmetic, no LLM: the same input always returns the same numbers. Input: points or table with x_column, y_column; optional metrics, predict_x, probability_queries. $0.50 per call.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "hubvibe_predictive_probability_engine"
  }
}

Input Schema

NameRequiredDescriptionDefault
alphaNo
tableNo
pointsNo
metricsNo
languageNo
max_rowsNo
x_columnNo
y_columnNo
predict_xNo
distribution_ofNo
probability_queriesNo

Output Schema

NameRequiredDescriptionDefault
resultYes
statusYes
workerYes
price_usdYes
receipt_urlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed19 schema fields changed
    • removedInput schema / properties / alpha / description
      Removed value: -"Significance level for p-value validation and intervals. Default 0.05."
    • removedInput schema / properties / distribution_of / description
      Removed value: -"Which values the normal model fits. Default y."
    • removedInput schema / properties / language / description
      Removed value: -"Optional BCP-47 language tag (en, ja, ko, pt-BR): the human-readable strings of the result (notes, details, reasons) are translated into this language; data, codes, numbers and URLs are untouched. Default: as produced."
    • removedInput schema / properties / max_rows / description
      Removed value: -"Rows to read from `table`, default 10000. A larger table is reduced to this many rows by FARM_FINGERPRINT order, so the same table always yields the same rows."
    • removedInput schema / properties / metrics / description
      Removed value: -"Which results to compute. Default: linear_regression, normal_distribution and p_values, plus prediction when predict_x is given."
    • removedInput schema / properties / points / description
      Removed value: -"The data: [x, y] pairs (or {x, y} objects), 2 to 100000 of them; at least 3 for a regression. Use this OR `table`."
    • changedInput schema / properties / points / items / oneOf
      Previous value: -[
      -  {
      -    "description": "[x, y]",
      -    "items": {
      -      "type": "number"
      -    },
      -    "maxItems": 2,
      -    "minItems": 2,
      -    "type": "array"
      -  },
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "x": {
      -        "type": "number"
      -      },
      -      "y": {
      -        "type": "number"
      -      }
      -    },
      -    "required": [
      -      "x",
      -      "y"
      -    ],
      -    "type": "object"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "type": "number"
      +    },
      +    "maxItems": 2,
      +    "minItems": 2,
      +    "type": "array"
      +  },
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "x": {
      +        "type": "number"
      +      },
      +      "y": {
      +        "type": "number"
      +      }
      +    },
      +    "required": [
      +      "x",
      +      "y"
      +    ],
      +    "type": "object"
      +  }
      +]
    • removedInput schema / properties / predict_x / description
      Removed value: -"x values to predict y at, with mean and prediction intervals."
    • removedInput schema / properties / probability_queries / description
      Removed value: -"Probabilities to read off the fitted normal model: {\"below\": v}, {\"above\": v} or {\"between\": [a, b]}."
    • removedInput schema / properties / table / description
      Removed value: -"BigQuery table to read instead of `points`: project.dataset.table, readable by the node's service account (public datasets are). Needs x_column and y_column."
    • removedInput schema / properties / x_column / description
      Removed value: -"Numeric column for x, with `table`."
    • removedInput schema / properties / y_column / description
      Removed value: -"Numeric column for y, with `table`."
    • removedOutput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • removedOutput schema / properties / attribution
      Removed value: -{
      -  "items": {},
      -  "type": "array"
      -}
    • removedOutput schema / properties / billing_warning
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / provenance
      Removed value: -{
      -  "type": "object"
      -}
    • removedOutput schema / properties / receipt_id
      Removed value: -{
      -  "type": "string"
      -}
    • removedOutput schema / properties / status / type
      Removed value: -"string"
    • changedOutput schema / required
      Previous value: -[
      -  "status",
      -  "worker",
      -  "price_usd",
      -  "result",
      -  "provenance",
      -  "receipt_id",
      -  "receipt_url"
      -]New value: +[
      +  "status",
      +  "worker",
      +  "price_usd",
      +  "result",
      +  "receipt_url"
      +]
  2. Changed2 schema fields changed
    • addedInput schema / minProperties
      Added value: +1
    • removedInput schema / oneOf
      Removed value: -[
      -  {
      -    "required": [
      -      "points"
      -    ]
      -  },
      -  {
      -    "required": [
      -      "table",
      -      "x_column",
      -      "y_column"
      -    ]
      -  }
      -]
  3. Changed23 schema fields changed
    • removedOutput schema / description
      Removed value: -"The 200 body of every paid /work call. `result` is the worker's own output (its schema is per route); everything else is the same on every /work route. A receipt for the job is at `receipt_url`."
    • removedOutput schema / properties / attribution / description
      Removed value: -"Present only when the result's text was machine-translated: the credit to show with it."
    • removedOutput schema / properties / attribution / items / description
      Removed value: -"A credit."
    • removedOutput schema / properties / attribution / items / properties
      Removed value: -{
      -  "text": {
      -    "description": "Credit.",
      -    "examples": [
      -      "Translated by Google"
      -    ],
      -    "type": "string"
      -  },
      -  "url": {
      -    "description": "Link.",
      -    "examples": [
      -      "https://translate.google.com"
      -    ],
      -    "type": "string"
      -  }
      -}
    • removedOutput schema / properties / attribution / items / required
      Removed value: -[
      -  "text",
      -  "url"
      -]
    • removedOutput schema / properties / attribution / items / type
      Removed value: -"object"
    • removedOutput schema / properties / billing_warning / description
      Removed value: -"Present only when the charge was recorded with a caveat."
    • removedOutput schema / properties / billing_warning / examples
      Removed value: -[
      -  "settlement pending"
      -]
    • removedOutput schema / properties / price_usd / description
      Removed value: -"What this call cost, in USD."
    • removedOutput schema / properties / price_usd / examples
      Removed value: -[
      -  0.02
      -]
    • removedOutput schema / properties / provenance / description
      Removed value: -"How the result was produced: which providers ran and how long each took."
    • removedOutput schema / properties / provenance / properties
      Removed value: -{
      -  "attempts": {
      -    "description": "Provider attempts made, including retries and failovers.",
      -    "examples": [
      -      1
      -    ],
      -    "type": "integer"
      -  },
      -  "elapsed_ms": {
      -    "description": "Wall-clock milliseconds for the whole job.",
      -    "examples": [
      -      340
      -    ],
      -    "type": "integer"
      -  },
      -  "providers_used": {
      -    "description": "Providers that served the job.",
      -    "examples": [
      -      [
      -        "coinbase-advanced-trade-public"
      -      ]
      -    ],
      -    "items": {
      -      "description": "Provider name.",
      -      "examples": [
      -        "coinbase-advanced-trade-public"
      -      ],
      -      "type": "string"
      -    },
      -    "type": "array"
      -  },
      -  "steps": {
      -    "description": "Every step the job ran, in order.",
      -    "items": {
      -      "description": "One step of the job.",
      -      "properties": {
      -        "ms": {
      -          "description": "Milliseconds the step took.",
      -          "examples": [
      -            312
      -          ],
      -          "type": "integer"
      -        },
      -        "ok": {
      -          "description": "Whether the step succeeded.",
      -          "examples": [
      -            true
      -          ],
      -          "type": "boolean"
      -        },
      -        "provider": {
      -          "description": "Provider that served the step.",
      -          "examples": [
      -            "coinbase-advanced-trade-public"
      -          ],
      -          "type": "string"
      -        },
      -        "reason": {
      -          "description": "Failure reason, on a failed step.",
      -          "examples": [
      -            "provider_timeout"
      -          ],
      -          "type": "string"
      -        },
      -        "step": {
      -          "description": "Step name inside the worker.",
      -          "examples": [
      -            "quote"
      -          ],
      -          "type": "string"
      -        }
      -      },
      -      "required": [
      -        "step",
      -        "ok",
      -        "ms"
      -      ],
      -      "type": "object"
      -    },
      -    "type": "array"
      -  }
      -}
    • removedOutput schema / properties / provenance / required
      Removed value: -[
      -  "steps",
      -  "providers_used",
      -  "attempts",
      -  "elapsed_ms"
      -]
    • removedOutput schema / properties / receipt_id / description
      Removed value: -"Receipt id for this job."
    • removedOutput schema / properties / receipt_id / examples
      Removed value: -[
      -  "rcpt_9f1c2b3a4d5e6f70"
      -]
    • removedOutput schema / properties / receipt_url / description
      Removed value: -"Where to fetch the machine-readable receipt (free, no payment)."
    • removedOutput schema / properties / receipt_url / examples
      Removed value: -[
      -  "/work/receipts/rcpt_9f1c2b3a4d5e6f70"
      -]
    • removedOutput schema / properties / result / properties
      Removed value: -{
      -  "alpha": {
      -    "description": "Significance level used.",
      -    "examples": [
      -      0.05
      -    ],
      -    "type": "number"
      -  },
      -  "confidence_level": {
      -    "description": "1 - alpha: the level of every interval.",
      -    "examples": [
      -      0.95
      -    ],
      -    "type": "number"
      -  },
      -  "linear_regression": {
      -    "description": "Ordinary least squares fit of y on x; null when not requested.",
      -    "properties": {
      -      "adjusted_r_squared": {
      -        "description": "R^2 adjusted for degrees of freedom.",
      -        "examples": [
      -          0.995
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "degrees_of_freedom": {
      -        "description": "n - 2.",
      -        "examples": [
      -          3
      -        ],
      -        "type": "integer"
      -      },
      -      "f_statistic": {
      -        "description": "F statistic of the regression (t^2); null when undefined.",
      -        "examples": [
      -          773
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "intercept": {
      -        "description": "OLS intercept.",
      -        "examples": [
      -          0.08
      -        ],
      -        "type": "number"
      -      },
      -      "intercept_ci": {
      -        "description": "Lower and upper bound at the confidence level.",
      -        "examples": [
      -          [
      -            1.43,
      -            2.53
      -          ]
      -        ],
      -        "items": {
      -          "description": "Bound.",
      -          "examples": [
      -            0
      -          ],
      -          "type": "number"
      -        },
      -        "type": "array"
      -      },
      -      "intercept_std_error": {
      -        "description": "Standard error of the intercept.",
      -        "examples": [
      -          0.236
      -        ],
      -        "type": "number"
      -      },
      -      "intercept_t": {
      -        "description": "t statistic of the intercept; null when undefined.",
      -        "examples": [
      -          0.34
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "r": {
      -        "description": "Pearson correlation; null when y is constant.",
      -        "examples": [
      -          0.998
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "r_squared": {
      -        "description": "Coefficient of determination; null when y is constant.",
      -        "examples": [
      -          0.996
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "residual_std_error": {
      -        "description": "Standard error of the residuals, sqrt(SSE / df).",
      -        "examples": [
      -          0.225
      -        ],
      -        "type": "number"
      -      },
      -      "slope": {
      -        "description": "OLS slope.",
      -        "examples": [
      -          1.98
      -        ],
      -        "type": "number"
      -      },
      -      "slope_ci": {
      -        "description": "Lower and upper bound at the confidence level.",
      -        "examples": [
      -          [
      -            1.43,
      -            2.53
      -          ]
      -        ],
      -        "items": {
      -          "description": "Bound.",
      -          "examples": [
      -            0
      -          ],
      -          "type": "number"
      -        },
      -        "type": "array"
      -      },
      -      "slope_std_error": {
      -        "description": "Standard error of the slope.",
      -        "examples": [
      -          0.071
      -        ],
      -        "type": "number"
      -      },
      -      "slope_t": {
      -        "description": "t statistic of the slope; null when undefined.",
      -        "examples": [
      -          27.8
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "sse": {
      -        "description": "Sum of squared residuals.",
      -        "examples": [
      -          0.152
      -        ],
      -        "type": "number"
      -      },
      -      "sst": {
      -        "description": "Total sum of squares of y.",
      -        "examples": [
      -          39.4
      -        ],
      -        "type": "number"
      -      },
      -      "t_critical": {
      -        "description": "Two-sided t critical value at alpha with df degrees of freedom.",
      -        "examples": [
      -          3.18
      -        ],
      -        "type": "number"
      -      },
      -      "x_mean": {
      -        "description": "Mean of x.",
      -        "examples": [
      -          3
      -        ],
      -        "type": "number"
      -      },
      -      "y_mean": {
      -        "description": "Mean of y.",
      -        "examples": [
      -          6.02
      -        ],
      -        "type": "number"
      -      }
      -    },
      -    "required": [
      -      "slope",
      -      "intercept",
      -      "r",
      -      "r_squared",
      -      "adjusted_r_squared",
      -      "slope_std_error",
      -      "intercept_std_error",
      -      "residual_std_error",
      -      "degrees_of_freedom",
      -      "slope_t",
      -      "intercept_t",
      -      "t_critical",
      -      "slope_ci",
      -      "intercept_ci",
      -      "f_statistic",
      -      "sse",
      -      "sst",
      -      "x_mean",
      -      "y_mean"
      -    ],
      -    "type": [
      -      "object",
      -      "null"
      -    ]
      -  },
      -  "method": {
      -    "description": "How the numbers were produced.",
      -    "examples": [
      -      "Ordinary least squares (closed form). Student t p-values from the regularised incomplete beta function..."
      -    ],
      -    "type": "string"
      -  },
      -  "metrics": {
      -    "description": "Metrics computed, in canonical order.",
      -    "examples": [
      -      [
      -        "linear_regression",
      -        "normal_distribution",
      -        "p_values",
      -        "prediction"
      -      ]
      -    ],
      -    "items": {
      -      "description": "Metric name.",
      -      "enum": [
      -        "linear_regression",
      -        "normal_distribution",
      -        "p_values",
      -        "prediction"
      -      ],
      -      "examples": [
      -        "linear_regression"
      -      ],
      -      "type": "string"
      -    },
      -    "type": "array"
      -  },
      -  "n": {
      -    "description": "Number of points.",
      -    "examples": [
      -      5
      -    ],
      -    "type": "integer"
      -  },
      -  "normal_distribution": {
      -    "description": "Normal model of the chosen values; null when not requested.",
      -    "properties": {
      -      "excess_kurtosis": {
      -        "description": "Excess kurtosis; null when the values are constant.",
      -        "examples": [
      -          -1.3
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "max": {
      -        "description": "Largest value.",
      -        "examples": [
      -          10.1
      -        ],
      -        "type": "number"
      -      },
      -      "mean": {
      -        "description": "Sample mean.",
      -        "examples": [
      -          6.02
      -        ],
      -        "type": "number"
      -      },
      -      "median": {
      -        "description": "Median of the values.",
      -        "examples": [
      -          6.2
      -        ],
      -        "type": "number"
      -      },
      -      "min": {
      -        "description": "Smallest value.",
      -        "examples": [
      -          2.1
      -        ],
      -        "type": "number"
      -      },
      -      "normality": {
      -        "description": "Jarque-Bera normality test; null when the values are constant.",
      -        "properties": {
      -          "null_hypothesis": {
      -            "description": "What the test rejects.",
      -            "examples": [
      -              "the values are normally distributed"
      -            ],
      -            "type": "string"
      -          },
      -          "p_value": {
      -            "description": "Chi-square(2) p-value, exp(-JB/2).",
      -            "examples": [
      -              0.81
      -            ],
      -            "type": "number"
      -          },
      -          "reject_at_alpha": {
      -            "description": "p_value < alpha: not normal at this alpha.",
      -            "examples": [
      -              false
      -            ],
      -            "type": "boolean"
      -          },
      -          "statistic": {
      -            "description": "Jarque-Bera statistic.",
      -            "examples": [
      -              0.42
      -            ],
      -            "type": "number"
      -          },
      -          "test": {
      -            "const": "jarque_bera",
      -            "description": "The test.",
      -            "type": "string"
      -          }
      -        },
      -        "required": [
      -          "test",
      -          "statistic",
      -          "p_value",
      -          "null_hypothesis",
      -          "reject_at_alpha"
      -        ],
      -        "type": [
      -          "object",
      -          "null"
      -        ]
      -      },
      -      "of": {
      -        "description": "Which values the model fits.",
      -        "enum": [
      -          "y",
      -          "x",
      -          "residuals"
      -        ],
      -        "examples": [
      -          "y"
      -        ],
      -        "type": "string"
      -      },
      -      "probabilities": {
      -        "description": "Answers to probability_queries, in order.",
      -        "examples": [
      -          [
      -            {
      -              "probability": 0.736,
      -              "query": {
      -                "below": 8
      -              }
      -            }
      -          ]
      -        ],
      -        "items": {
      -          "properties": {
      -            "probability": {
      -              "description": "Probability under the fitted normal.",
      -              "examples": [
      -                0.736
      -              ],
      -              "type": "number"
      -            },
      -            "query": {
      -              "description": "The query as sent.",
      -              "examples": [
      -                {
      -                  "below": 8
      -                }
      -              ],
      -              "type": [
      -                "object"
      -              ]
      -            }
      -          },
      -          "required": [
      -            "query",
      -            "probability"
      -          ],
      -          "type": "object"
      -        },
      -        "type": "array"
      -      },
      -      "quantiles": {
      -        "description": "Quantiles of the fitted normal; null when degenerate.",
      -        "items": {
      -          "properties": {
      -            "p": {
      -              "description": "Probability.",
      -              "examples": [
      -                0.95
      -              ],
      -              "type": "number"
      -            },
      -            "value": {
      -              "description": "Value at that quantile.",
      -              "examples": [
      -                11.19
      -              ],
      -              "type": "number"
      -            }
      -          },
      -          "required": [
      -            "p",
      -            "value"
      -          ],
      -          "type": "object"
      -        },
      -        "type": [
      -          "array",
      -          "null"
      -        ]
      -      },
      -      "skewness": {
      -        "description": "Sample skewness; null when the values are constant.",
      -        "examples": [
      -          0.05
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "std_dev": {
      -        "description": "Sample standard deviation (n - 1).",
      -        "examples": [
      -          3.14
      -        ],
      -        "type": "number"
      -      },
      -      "variance": {
      -        "description": "Sample variance (n - 1).",
      -        "examples": [
      -          9.86
      -        ],
      -        "type": "number"
      -      }
      -    },
      -    "required": [
      -      "of",
      -      "mean",
      -      "std_dev",
      -      "variance",
      -      "min",
      -      "max",
      -      "median",
      -      "skewness",
      -      "excess_kurtosis",
      -      "quantiles",
      -      "probabilities",
      -      "normality"
      -    ],
      -    "type": [
      -      "object",
      -      "null"
      -    ]
      -  },
      -  "notes": {
      -    "description": "Caveats about the input; empty when there are none.",
      -    "examples": [
      -      []
      -    ],
      -    "items": {
      -      "description": "A caveat about a degenerate input.",
      -      "examples": [
      -        "The points lie exactly on a line."
      -      ],
      -      "type": "string"
      -    },
      -    "type": "array"
      -  },
      -  "p_values": {
      -    "description": "Hypothesis tests validated at alpha; null when not requested.",
      -    "properties": {
      -      "intercept": {
      -        "description": "One two-sided Student t test.",
      -        "properties": {
      -          "null_hypothesis": {
      -            "description": "What the test rejects.",
      -            "examples": [
      -              "slope = 0 (no linear relationship)"
      -            ],
      -            "type": "string"
      -          },
      -          "p_value": {
      -            "description": "Two-sided p-value; null when undefined.",
      -            "examples": [
      -              0.0015
      -            ],
      -            "type": [
      -              "number",
      -              "null"
      -            ]
      -          },
      -          "significant_at_alpha": {
      -            "description": "p_value < alpha.",
      -            "examples": [
      -              true
      -            ],
      -            "type": [
      -              "boolean",
      -              "null"
      -            ]
      -          },
      -          "t": {
      -            "description": "Student t statistic; null when undefined (a perfect fit).",
      -            "examples": [
      -              11.4
      -            ],
      -            "type": [
      -              "number",
      -              "null"
      -            ]
      -          }
      -        },
      -        "required": [
      -          "null_hypothesis",
      -          "t",
      -          "p_value",
      -          "significant_at_alpha"
      -        ],
      -        "type": "object"
      -      },
      -      "normality_of_residuals": {
      -        "description": "Jarque-Bera normality test; null when the values are constant.",
      -        "properties": {
      -          "null_hypothesis": {
      -            "description": "What the test rejects.",
      -            "examples": [
      -              "the values are normally distributed"
      -            ],
      -            "type": "string"
      -          },
      -          "p_value": {
      -            "description": "Chi-square(2) p-value, exp(-JB/2).",
      -            "examples": [
      -              0.81
      -            ],
      -            "type": "number"
      -          },
      -          "reject_at_alpha": {
      -            "description": "p_value < alpha: not normal at this alpha.",
      -            "examples": [
      -              false
      -            ],
      -            "type": "boolean"
      -          },
      -          "statistic": {
      -            "description": "Jarque-Bera statistic.",
      -            "examples": [
      -              0.42
      -            ],
      -            "type": "number"
      -          },
      -          "test": {
      -            "const": "jarque_bera",
      -            "description": "The test.",
      -            "type": "string"
      -          }
      -        },
      -        "required": [
      -          "test",
      -          "statistic",
      -          "p_value",
      -          "null_hypothesis",
      -          "reject_at_alpha"
      -        ],
      -        "type": [
      -          "object",
      -          "null"
      -        ]
      -      },
      -      "slope": {
      -        "description": "One two-sided Student t test.",
      -        "properties": {
      -          "null_hypothesis": {
      -            "description": "What the test rejects.",
      -            "examples": [
      -              "slope = 0 (no linear relationship)"
      -            ],
      -            "type": "string"
      -          },
      -          "p_value": {
      -            "description": "Two-sided p-value; null when undefined.",
      -            "examples": [
      -              0.0015
      -            ],
      -            "type": [
      -              "number",
      -              "null"
      -            ]
      -          },
      -          "significant_at_alpha": {
      -            "description": "p_value < alpha.",
      -            "examples": [
      -              true
      -            ],
      -            "type": [
      -              "boolean",
      -              "null"
      -            ]
      -          },
      -          "t": {
      -            "description": "Student t statistic; null when undefined (a perfect fit).",
      -            "examples": [
      -              11.4
      -            ],
      -            "type": [
      -              "number",
      -              "null"
      -            ]
      -          }
      -        },
      -        "required": [
      -          "null_hypothesis",
      -          "t",
      -          "p_value",
      -          "significant_at_alpha"
      -        ],
      -        "type": "object"
      -      }
      -    },
      -    "required": [
      -      "slope",
      -      "intercept",
      -      "normality_of_residuals"
      -    ],
      -    "type": [
      -      "object",
      -      "null"
      -    ]
      -  },
      -  "prediction": {
      -    "description": "One entry per predict_x; null when not requested.",
      -    "items": {
      -      "properties": {
      -        "mean_ci": {
      -          "description": "Lower and upper bound at the confidence level.",
      -          "examples": [
      -            [
      -              1.43,
      -              2.53
      -            ]
      -          ],
      -          "items": {
      -            "description": "Bound.",
      -            "examples": [
      -              0
      -            ],
      -            "type": "number"
      -          },
      -          "type": "array"
      -        },
      -        "prediction_interval": {
      -          "description": "Lower and upper bound at the confidence level.",
      -          "examples": [
      -            [
      -              1.43,
      -              2.53
      -            ]
      -          ],
      -          "items": {
      -            "description": "Bound.",
      -            "examples": [
      -              0
      -            ],
      -            "type": "number"
      -          },
      -          "type": "array"
      -        },
      -        "x": {
      -          "description": "The x asked for.",
      -          "examples": [
      -            6
      -          ],
      -          "type": "number"
      -        },
      -        "y_hat": {
      -          "description": "Predicted y.",
      -          "examples": [
      -            11.96
      -          ],
      -          "type": "number"
      -        }
      -      },
      -      "required": [
      -        "x",
      -        "y_hat",
      -        "mean_ci",
      -        "prediction_interval"
      -      ],
      -      "type": "object"
      -    },
      -    "type": [
      -      "array",
      -      "null"
      -    ]
      -  },
      -  "source": {
      -    "description": "Where the data came from and how much of it was used.",
      -    "properties": {
      -      "gib_processed": {
      -        "description": "Gibibytes BigQuery scanned; null for inline points.",
      -        "examples": [
      -          null
      -        ],
      -        "type": [
      -          "number",
      -          "null"
      -        ]
      -      },
      -      "rows_available": {
      -        "description": "Rows with finite x and y in the table; null for inline points.",
      -        "examples": [
      -          null
      -        ],
      -        "type": [
      -          "integer",
      -          "null"
      -        ]
      -      },
      -      "rows_used": {
      -        "description": "Points the statistics were computed from.",
      -        "examples": [
      -          5
      -        ],
      -        "type": "integer"
      -      },
      -      "sampled": {
      -        "description": "True when the table had more usable rows than were read.",
      -        "examples": [
      -          false
      -        ],
      -        "type": "boolean"
      -      },
      -      "sql": {
      -        "description": "The read-only SQL that ran, when source is bigquery.",
      -        "examples": [
      -          null
      -        ],
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "table": {
      -        "description": "BigQuery table read, when source is bigquery.",
      -        "examples": [
      -          null
      -        ],
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "type": {
      -        "description": "Where the points came from.",
      -        "enum": [
      -          "points",
      -          "bigquery"
      -        ],
      -        "examples": [
      -          "points"
      -        ],
      -        "type": "string"
      -      },
      -      "x_column": {
      -        "description": "Column used for x, when source is bigquery.",
      -        "examples": [
      -          null
      -        ],
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      },
      -      "y_column": {
      -        "description": "Column used for y, when source is bigquery.",
      -        "examples": [
      -          null
      -        ],
      -        "type": [
      -          "string",
      -          "null"
      -        ]
      -      }
      -    },
      -    "required": [
      -      "type",
      -      "table",
      -      "x_column",
      -      "y_column",
      -      "sql",
      -      "rows_available",
      -      "rows_used",
      -      "sampled",
      -      "gib_processed"
      -    ],
      -    "type": "object"
      -  }
      -}
    • removedOutput schema / properties / result / required
      Removed value: -[
      -  "source",
      -  "n",
      -  "alpha",
      -  "confidence_level",
      -  "metrics",
      -  "linear_regression",
      -  "normal_distribution",
      -  "p_values",
      -  "prediction",
      -  "notes",
      -  "method"
      -]
    • removedOutput schema / properties / status / description
      Removed value: -"Present only on a delivered result."
    • removedOutput schema / properties / worker / description
      Removed value: -"Catalog name of the worker that ran."
    • removedOutput schema / properties / worker / examples
      Removed value: -[
      -  "market.quote"
      -]
    • removedOutput schema / title
      Removed value: -"stats.probability response"
  4. Changed1 schema field changed
    • addedOutput schema / properties / attribution
      Added value: +{
      +  "description": "Present only when the result's text was machine-translated: the credit to show with it.",
      +  "items": {
      +    "description": "A credit.",
      +    "properties": {
      +      "text": {
      +        "description": "Credit.",
      +        "examples": [
      +          "Translated by Google"
      +        ],
      +        "type": "string"
      +      },
      +      "url": {
      +        "description": "Link.",
      +        "examples": [
      +          "https://translate.google.com"
      +        ],
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "text",
      +      "url"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  5. Changed1 schema field changed
    • addedInput schema / properties / language
      Added value: +{
      +  "description": "Optional BCP-47 language tag (en, ja, ko, pt-BR): the human-readable strings of the result (notes, details, reasons) are translated into this language; data, codes, numbers and URLs are untouched. Default: as produced.",
      +  "maxLength": 35,
      +  "pattern": "^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$",
      +  "type": "string"
      +}
  6. Changed1 schema field changed
    • changedOutput schema / description
      Previous value: -"The 200 body of every paid /work call. `result` is the worker's own output (its schema is per route); everything else is the same on all 38 routes. A receipt for the job is at `receipt_url`."New value: +"The 200 body of every paid /work call. `result` is the worker's own output (its schema is per route); everything else is the same on every /work route. A receipt for the job is at `receipt_url`."
  7. Added

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, non-destructive, and open-world behavior. The description adds useful behavioral context beyond that: deterministic arithmetic with no LLM, identical output for identical input, and a $0.50 per-call cost. It does not cover authentication, rate limits, or BigQuery access requirements, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded with the core capability, then input modes, determinism, parameter names, and pricing. Most sentences earn their place, though it reads as a feature list and repeats some framing from the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is complex with 11 parameters and no schema descriptions, but it has an output schema and rich annotations. The description covers the main purpose, input modes, determinism, and cost, but is not complete enough on usage selection or several parameter meanings for a fully self-contained definition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning. It names the major inputs (points, table, x_column, y_column, metrics, predict_x, probability_queries) and explains the inline-vs-BigQuery input distinction, but it leaves alpha, language, max_rows, and distribution_of unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly names a specific analytical resource: least-squares regression, normal-distribution fitting, intervals, and p-values. An agent can understand the tool's function without opening the schema, but there is no explicit differentiation from sibling analytical tools such as data_forecast or finance_analytics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the listed statistical capabilities: an agent can infer this is for regression and probability queries. However, there is no explicit when-to-use guidance, no exclusions, and no named alternatives to help choose among sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.