Skip to main content
Glama

Sitelemetry

by com.sitelemetry
OverviewDiscussionsAdmin

Accessibility (WCAG) audit

audit_accessibility

Static WCAG 2.2 accessibility audit from the DOM: image alt text, form labels, heading structure, landmarks, color-contrast signals, language attribute, duplicate ids, iframe titles. Returns violations with fixes. Provide target to start an audit, or jobId to poll a running one. Long audits may return status: running with a jobId. Wait retryAfterMs, then call the same tool using the returned pollArguments, including target and jobId, until it returns the final result. Copy pollArguments unchanged; do not add scan options. Clients that support jobId alone may also use it. Polling retrieves the same audit without starting another scan or reserving more quota. Do not present running as completed and do not start a replacement audit while it is running.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
langNoReport language (default en): en, tr, es, de, fr, pt, it, ja, zh.
jobIdNoResume an existing audit by polling this same tool with the returned pollArguments. Keep target and jobId unchanged. If repeating scan options, supply every original argument unchanged. Never invent a jobId.
targetNoTarget website URL or domain you own / are authorized to audit (e.g. https://example.com).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / anyOf
      Removed value: -[
-  {
-    "required": [
-      "target"
-    ]
-  },
-  {
-    "required": [
-      "jobId"
-    ]
-  }
-]
  2. Changed3 schema fields changed
    • changedInput schema / anyOf
      Previous value: -[
-  {
-    "required": [
-      "target"
-    ]
-  },
-  {
-    "maxProperties": 1,
-    "required": [
-      "jobId"
-    ]
-  }
-]New value: +[
+  {
+    "required": [
+      "target"
+    ]
+  },
+  {
+    "required": [
+      "jobId"
+    ]
+  }
+]
    • changedInput schema / properties / jobId / description
      Previous value: -"Resume an existing audit by polling this same tool with its returned jobId. Prefer jobId alone; if repeating other arguments, supply every original argument unchanged. Never invent a jobId."New value: +"Resume an existing audit by polling this same tool with the returned pollArguments. Keep target and jobId unchanged. If repeating scan options, supply every original argument unchanged. Never invent a jobId."
    • changedOutput schema / oneOf
      Previous value: -[
-  {
-    "oneOf": [
-      {
-        "additionalProperties": true,
-        "properties": {
-          "auditDetails": {
-            "additionalProperties": true,
-            "description": "Complete available scope, check states and measurement evidence; unmeasured checks are not passes.",
-            "type": "object"
-          },
-          "counts": {
-            "additionalProperties": false,
-            "description": "Finding totals grouped by normalized severity.",
-            "properties": {
-              "critical": {
-                "description": "Number of critical findings.",
-                "minimum": 0,
-                "type": "integer"
-              },
-              "high": {
-                "description": "Number of high-severity findings.",
-                "minimum": 0,
-                "type": "integer"
-              },
-              "info": {
-                "description": "Number of informational findings.",
-                "minimum": 0,
-                "type": "integer"
-              },
-              "low": {
-                "description": "Number of low-severity findings.",
-                "minimum": 0,
-                "type": "integer"
-              },
-              "medium": {
-                "description": "Number of medium-severity findings.",
-                "minimum": 0,
-                "type": "integer"
-              }
-            },
-            "required": [
-              "critical",
-              "high",
-              "medium",
-              "low",
-              "info"
-            ],
-            "type": "object"
-          },
-          "coverageStatus": {
-            "description": "Availability of measurements within the requested methods and account scope; not a claim to test every possible website behavior.",
-            "enum": [
-              "measured",
-              "partial",
-              "unavailable",
-              "not_applicable"
-            ],
-            "type": "string"
-          },
-          "executionComplete": {
-            "description": "Whether all requested pillar runners returned. This is separate from measurement coverage.",
-            "type": "boolean"
-          },
-          "findings": {
-            "description": "Prioritized findings with evidence, impact, and remediation.",
-            "items": {
-              "additionalProperties": false,
-              "properties": {
-                "category": {
-                  "description": "Stable audit category for grouping related findings.",
-                  "type": "string"
-                },
-                "evidence": {
-                  "description": "Bounded observation that supports the finding.",
-                  "type": "string"
-                },
-                "findingKey": {
-                  "description": "Deterministic pillar-scoped identity for before/after comparison.",
-                  "maxLength": 512,
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "impact": {
-                  "description": "Why the finding matters to the audited website.",
-                  "type": "string"
-                },
-                "location": {
-                  "description": "Observed URL or path with credentials and query secrets removed, when available.",
-                  "type": "string"
-                },
-                "remediation": {
-                  "description": "Concrete recommended fix or mitigation.",
-                  "type": "string"
-                },
-                "severity": {
-                  "description": "Normalized finding severity: critical, high, medium, low, or info.",
-                  "type": "string"
-                },
-                "title": {
-                  "description": "Short human-readable finding title.",
-                  "type": "string"
-                }
-              },
-              "required": [
-                "findingKey",
-                "severity",
-                "title",
-                "evidence",
-                "impact",
-                "remediation",
-                "category"
-              ],
-              "type": "object"
-            },
-            "type": "array"
-          },
-          "findingsTruncated": {
-            "description": "True when additional findings exist outside this response.",
-            "type": "boolean"
-          },
-          "grade": {
-            "description": "Human-readable grade, or null when unavailable.",
-            "type": [
-              "string",
-              "null"
-            ]
-          },
-          "kind": {
-            "description": "Audit pillar represented by this result.",
-            "type": "string"
-          },
-          "passingChecks": {
-            "description": "Number of checks that passed or reported protection.",
-            "minimum": 0,
-            "type": "integer"
-          },
-          "passingFindings": {
-            "description": "Positive observations retained with their complete evidence.",
-            "items": {
-              "additionalProperties": false,
-              "properties": {
-                "category": {
-                  "description": "Stable audit category for grouping related findings.",
-                  "type": "string"
-                },
-                "evidence": {
-                  "description": "Bounded observation that supports the finding.",
-                  "type": "string"
-                },
-                "findingKey": {
-                  "description": "Deterministic pillar-scoped identity for before/after comparison.",
-                  "maxLength": 512,
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "impact": {
-                  "description": "Why the finding matters to the audited website.",
-                  "type": "string"
-                },
-                "location": {
-                  "description": "Observed URL or path with credentials and query secrets removed, when available.",
-                  "type": "string"
-                },
-                "remediation": {
-                  "description": "Concrete recommended fix or mitigation.",
-                  "type": "string"
-                },
-                "severity": {
-                  "description": "Normalized finding severity: critical, high, medium, low, or info.",
-                  "type": "string"
-                },
-                "title": {
-                  "description": "Short human-readable finding title.",
-                  "type": "string"
-                }
-              },
-              "required": [
-                "findingKey",
-                "severity",
-                "title",
-                "evidence",
-                "impact",
-                "remediation",
-                "category"
-              ],
-              "type": "object"
-            },
-            "type": "array"
-          },
-          "returnedFindings": {
-            "description": "Number of findings included in this response.",
-            "minimum": 0,
-            "type": "integer"
-          },
-          "score": {
-            "description": "Measured score from 0 to 100, or null when unavailable.",
-            "type": [
-              "number",
-              "null"
-            ]
-          },
-          "status": {
-            "description": "Completed when requested measurements are available; partial when a requested runner or measurement is unavailable.",
-            "enum": [
-              "completed",
-              "partial"
-            ],
-            "type": "string"
-          },
-          "target": {
-            "description": "Canonical audited target.",
-            "type": "string"
-          },
-          "total": {
-            "description": "Total findings produced before response truncation.",
-            "minimum": 0,
-            "type": "integer"
-          }
-        },
-        "required": [
-          "target",
-          "kind",
-          "score",
-          "grade",
-          "counts",
-          "total",
-          "returnedFindings",
-          "findingsTruncated",
-          "passingChecks",
-          "findings"
-        ],
-        "type": "object"
-      },
-      {
-        "additionalProperties": false,
-        "properties": {
-          "executionComplete": {
-            "const": false,
-            "description": "False until the entire audit result is ready for delivery.",
-            "type": "boolean"
-          },
-          "jobId": {
-            "description": "Opaque temporary job identifier bound to this account, tool and MCP surface.",
-            "pattern": "^mj_[A-Za-z0-9_-]{32}$",
-            "type": "string"
-          },
-          "nextAction": {
-            "const": "poll_same_tool",
-            "description": "Call this same tool again with pollArguments.",
-            "type": "string"
-          },
-          "pollArguments": {
-            "additionalProperties": false,
-            "description": "Arguments for retrieving this existing audit without starting another scan.",
-            "properties": {
-              "jobId": {
-                "description": "The same opaque audit job identifier.",
-                "pattern": "^mj_[A-Za-z0-9_-]{32}$",
-                "type": "string"
-              }
-            },
-            "required": [
-              "jobId"
-            ],
-            "type": "object"
-          },
-          "retryAfterMs": {
-            "description": "Suggested delay in milliseconds before polling this job again.",
-            "minimum": 0,
-            "type": "integer"
-          },
-          "status": {
-            "const": "running",
-            "description": "The audit is still executing or completing durable delivery.",
-            "type": "string"
-          }
-        },
-        "required": [
-          "status",
-          "jobId",
-          "executionComplete",
-          "nextAction",
-          "pollArguments",
-          "retryAfterMs"
-        ],
-        "type": "object"
-      },
-      {
-        "additionalProperties": false,
-        "properties": {
-          "auditExecuted": {
-            "const": false,
-            "description": "This request did not execute a new audit.",
-            "type": "boolean"
-          },
-          "reason": {
-            "description": "The recoverable job request prerequisite.",
-            "enum": [
-              "audit_job_busy",
-              "audit_job_unavailable",
-              "audit_job_argument_mismatch",
-              "audit_job_invalid_arguments"
-            ],
-            "type": "string"
-          },
-          "status": {
-            "const": "action_required",
-            "description": "This request did not start a new audit.",
-            "type": "string"
-          },
-          "usageConsumed": {
-            "const": false,
-            "description": "This request did not consume additional audit allowance.",
-            "type": "boolean"
-          }
-        },
-        "required": [
-          "status",
-          "reason",
-          "auditExecuted",
-          "usageConsumed"
-        ],
-        "type": "object"
-      }
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "auditExecuted": {
-        "const": false,
-        "type": "boolean"
-      },
-      "reason": {
-        "enum": [
-          "entitlement_required",
-          "target_verification_required",
-          "target_reverification_required",
-          "verification_scope_required",
-          "usage_limit_reached",
-          "authorization_consent_required"
-        ],
-        "type": "string"
-      },
-      "status": {
-        "const": "action_required",
-        "type": "string"
-      },
-      "usageConsumed": {
-        "const": false,
-        "type": "boolean"
-      }
-    },
-    "required": [
-      "status",
-      "reason",
-      "auditExecuted",
-      "usageConsumed"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "oneOf": [
+      {
+        "additionalProperties": true,
+        "properties": {
+          "auditDetails": {
+            "additionalProperties": true,
+            "description": "Complete available scope, check states and measurement evidence; unmeasured checks are not passes.",
+            "type": "object"
+          },
+          "counts": {
+            "additionalProperties": false,
+            "description": "Finding totals grouped by normalized severity.",
+            "properties": {
+              "critical": {
+                "description": "Number of critical findings.",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "high": {
+                "description": "Number of high-severity findings.",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "info": {
+                "description": "Number of informational findings.",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "low": {
+                "description": "Number of low-severity findings.",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "medium": {
+                "description": "Number of medium-severity findings.",
+                "minimum": 0,
+                "type": "integer"
+              }
+            },
+            "required": [
+              "critical",
+              "high",
+              "medium",
+              "low",
+              "info"
+            ],
+            "type": "object"
+          },
+          "coverageStatus": {
+            "description": "Availability of measurements within the requested methods and account scope; not a claim to test every possible website behavior.",
+            "enum": [
+              "measured",
+              "partial",
+              "unavailable",
+              "not_applicable"
+            ],
+            "type": "string"
+          },
+          "executionComplete": {
+            "description": "Whether all requested pillar runners returned. This is separate from measurement coverage.",
+            "type": "boolean"
+          },
+          "findings": {
+            "description": "Prioritized findings with evidence, impact, and remediation.",
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "category": {
+                  "description": "Stable audit category for grouping related findings.",
+                  "type": "string"
+                },
+                "evidence": {
+                  "description": "Bounded observation that supports the finding.",
+                  "type": "string"
+                },
+                "findingKey": {
+                  "description": "Deterministic pillar-scoped identity for before/after comparison.",
+                  "maxLength": 512,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "impact": {
+                  "description": "Why the finding matters to the audited website.",
+                  "type": "string"
+                },
+                "location": {
+                  "description": "Observed URL or path with credentials and query secrets removed, when available.",
+                  "type": "string"
+                },
+                "remediation": {
+                  "description": "Concrete recommended fix or mitigation.",
+                  "type": "string"
+                },
+                "severity": {
+                  "description": "Normalized finding severity: critical, high, medium, low, or info.",
+                  "type": "string"
+                },
+                "title": {
+                  "description": "Short human-readable finding title.",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "findingKey",
+                "severity",
+                "title",
+                "evidence",
+                "impact",
+                "remediation",
+                "category"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "findingsTruncated": {
+            "description": "True when additional findings exist outside this response.",
+            "type": "boolean"
+          },
+          "grade": {
+            "description": "Human-readable grade, or null when unavailable.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "kind": {
+            "description": "Audit pillar represented by this result.",
+            "type": "string"
+          },
+          "passingChecks": {
+            "description": "Number of checks that passed or reported protection.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "passingFindings": {
+            "description": "Positive observations retained with their complete evidence.",
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "category": {
+                  "description": "Stable audit category for grouping related findings.",
+                  "type": "string"
+                },
+                "evidence": {
+                  "description": "Bounded observation that supports the finding.",
+                  "type": "string"
+                },
+                "findingKey": {
+                  "description": "Deterministic pillar-scoped identity for before/after comparison.",
+                  "maxLength": 512,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "impact": {
+                  "description": "Why the finding matters to the audited website.",
+                  "type": "string"
+                },
+                "location": {
+                  "description": "Observed URL or path with credentials and query secrets removed, when available.",
+                  "type": "string"
+                },
+                "remediation": {
+                  "description": "Concrete recommended fix or mitigation.",
+                  "type": "string"
+                },
+                "severity": {
+                  "description": "Normalized finding severity: critical, high, medium, low, or info.",
+                  "type": "string"
+                },
+                "title": {
+                  "description": "Short human-readable finding title.",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "findingKey",
+                "severity",
+                "title",
+                "evidence",
+                "impact",
+                "remediation",
+                "category"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "returnedFindings": {
+            "description": "Number of findings included in this response.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "score": {
+            "description": "Measured score from 0 to 100, or null when unavailable.",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "status": {
+            "description": "Completed when requested measurements are available; partial when a requested runner or measurement is unavailable.",
+            "enum": [
+              "completed",
+              "partial"
+            ],
+            "type": "string"
+          },
+          "target": {
+            "description": "Canonical audited target.",
+            "type": "string"
+          },
+          "total": {
+            "description": "Total findings produced before response truncation.",
+            "minimum": 0,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "target",
+          "kind",
+          "score",
+          "grade",
+          "counts",
+          "total",
+          "returnedFindings",
+          "findingsTruncated",
+          "passingChecks",
+          "findings"
+        ],
+        "type": "object"
+      },
+      {
+        "additionalProperties": false,
+        "properties": {
+          "executionComplete": {
+            "const": false,
+            "description": "False until the entire audit result is ready for delivery.",
+            "type": "boolean"
+          },
+          "jobId": {
+            "description": "Opaque temporary job identifier bound to this account, tool and MCP surface.",
+            "pattern": "^mj_[A-Za-z0-9_-]{32}$",
+            "type": "string"
+          },
+          "nextAction": {
+            "const": "poll_same_tool",
+            "description": "Call this same tool again with pollArguments.",
+            "type": "string"
+          },
+          "pollArguments": {
+            "additionalProperties": false,
+            "description": "Copy these arguments unchanged to retrieve this existing audit without starting another scan. The public target supports clients that require a target on every call.",
+            "properties": {
+              "jobId": {
+                "description": "The same opaque audit job identifier.",
+                "pattern": "^mj_[A-Za-z0-9_-]{32}$",
+                "type": "string"
+              },
+              "target": {
+                "description": "Public polling target for this job, without URL credentials, query or fragment. It does not change the original scan target.",
+                "maxLength": 2048,
+                "type": "string"
+              }
+            },
+            "required": [
+              "jobId"
+            ],
+            "type": "object"
+          },
+          "retryAfterMs": {
+            "description": "Suggested delay in milliseconds before polling this job again.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "status": {
+            "const": "running",
+            "description": "The audit is still executing or completing durable delivery.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "status",
+          "jobId",
+          "executionComplete",
+          "nextAction",
+          "pollArguments",
+          "retryAfterMs"
+        ],
+        "type": "object"
+      },
+      {
+        "additionalProperties": false,
+        "properties": {
+          "auditExecuted": {
+            "const": false,
+            "description": "This request did not execute a new audit.",
+            "type": "boolean"
+          },
+          "reason": {
+            "description": "The recoverable job request prerequisite.",
+            "enum": [
+              "audit_job_busy",
+              "audit_job_unavailable",
+              "audit_job_argument_mismatch",
+              "audit_job_invalid_arguments"
+            ],
+            "type": "string"
+          },
+          "status": {
+            "const": "action_required",
+            "description": "This request did not start a new audit.",
+            "type": "string"
+          },
+          "usageConsumed": {
+            "const": false,
+            "description": "This request did not consume additional audit allowance.",
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "status",
+          "reason",
+          "auditExecuted",
+          "usageConsumed"
+        ],
+        "type": "object"
+      }
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "auditExecuted": {
+        "const": false,
+        "type": "boolean"
+      },
+      "reason": {
+        "enum": [
+          "entitlement_required",
+          "target_verification_required",
+          "target_reverification_required",
+          "verification_scope_required",
+          "usage_limit_reached",
+          "authorization_consent_required"
+        ],
+        "type": "string"
+      },
+      "status": {
+        "const": "action_required",
+        "type": "string"
+      },
+      "usageConsumed": {
+        "const": false,
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "status",
+      "reason",
+      "auditExecuted",
+      "usageConsumed"
+    ],
+    "type": "object"
+  }
+]
  3. Changed1 schema field changed
    • changedOutput schema / oneOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "properties": {
-      "auditDetails": {
-        "additionalProperties": true,
-        "description": "Complete available scope, check states and measurement evidence; unmeasured checks are not passes.",
-        "type": "object"
-      },
-      "counts": {
-        "additionalProperties": false,
-        "description": "Finding totals grouped by normalized severity.",
-        "properties": {
-          "critical": {
-            "description": "Number of critical findings.",
-            "minimum": 0,
-            "type": "integer"
-          },
-          "high": {
-            "description": "Number of high-severity findings.",
-            "minimum": 0,
-            "type": "integer"
-          },
-          "info": {
-            "description": "Number of informational findings.",
-            "minimum": 0,
-            "type": "integer"
-          },
-          "low": {
-            "description": "Number of low-severity findings.",
-            "minimum": 0,
-            "type": "integer"
-          },
-          "medium": {
-            "description": "Number of medium-severity findings.",
-            "minimum": 0,
-            "type": "integer"
-          }
-        },
-        "required": [
-          "critical",
-          "high",
-          "medium",
-          "low",
-          "info"
-        ],
-        "type": "object"
-      },
-      "coverageStatus": {
-        "description": "Availability of measurements within the requested methods and account scope; not a claim to test every possible website behavior.",
-        "enum": [
-          "measured",
-          "partial",
-          "unavailable",
-          "not_applicable"
-        ],
-        "type": "string"
-      },
-      "executionComplete": {
-        "description": "Whether all requested pillar runners returned. This is separate from measurement coverage.",
-        "type": "boolean"
-      },
-      "findings": {
-        "description": "Prioritized findings with evidence, impact, and remediation.",
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "category": {
-              "description": "Stable audit category for grouping related findings.",
-              "type": "string"
-            },
-            "evidence": {
-              "description": "Bounded observation that supports the finding.",
-              "type": "string"
-            },
-            "findingKey": {
-              "description": "Deterministic pillar-scoped identity for before/after comparison.",
-              "maxLength": 512,
-              "minLength": 1,
-              "type": "string"
-            },
-            "impact": {
-              "description": "Why the finding matters to the audited website.",
-              "type": "string"
-            },
-            "location": {
-              "description": "Observed URL or path with credentials and query secrets removed, when available.",
-              "type": "string"
-            },
-            "remediation": {
-              "description": "Concrete recommended fix or mitigation.",
-              "type": "string"
-            },
-            "severity": {
-              "description": "Normalized finding severity: critical, high, medium, low, or info.",
-              "type": "string"
-            },
-            "title": {
-              "description": "Short human-readable finding title.",
-              "type": "string"
-            }
-          },
-          "required": [
-            "findingKey",
-            "severity",
-            "title",
-            "evidence",
-            "impact",
-            "remediation",
-            "category"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "findingsTruncated": {
-        "description": "True when additional findings exist outside this response.",
-        "type": "boolean"
-      },
-      "grade": {
-        "description": "Human-readable grade, or null when unavailable.",
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "kind": {
-        "description": "Audit pillar represented by this result.",
-        "type": "string"
-      },
-      "passingChecks": {
-        "description": "Number of checks that passed or reported protection.",
-        "minimum": 0,
-        "type": "integer"
-      },
-      "passingFindings": {
-        "description": "Positive observations retained with their complete evidence.",
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "category": {
-              "description": "Stable audit category for grouping related findings.",
-              "type": "string"
-            },
-            "evidence": {
-              "description": "Bounded observation that supports the finding.",
-              "type": "string"
-            },
-            "findingKey": {
-              "description": "Deterministic pillar-scoped identity for before/after comparison.",
-              "maxLength": 512,
-              "minLength": 1,
-              "type": "string"
-            },
-            "impact": {
-              "description": "Why the finding matters to the audited website.",
-              "type": "string"
-            },
-            "location": {
-              "description": "Observed URL or path with credentials and query secrets removed, when available.",
-              "type": "string"
-            },
-            "remediation": {
-              "description": "Concrete recommended fix or mitigation.",
-              "type": "string"
-            },
-            "severity": {
-              "description": "Normalized finding severity: critical, high, medium, low, or info.",
-              "type": "string"
-            },
-            "title": {
-              "description": "Short human-readable finding title.",
-              "type": "string"
-            }
-          },
-          "required": [
-            "findingKey",
-            "severity",
-            "title",
-            "evidence",
-            "impact",
-            "remediation",
-            "category"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "returnedFindings": {
-        "description": "Number of findings included in this response.",
-        "minimum": 0,
-        "type": "integer"
-      },
-      "score": {
-        "description": "Measured score from 0 to 100, or null when unavailable.",
-        "type": [
-          "number",
-          "null"
-        ]
-      },
-      "status": {
-        "description": "Completed when requested measurements are available; partial when a requested runner or measurement is unavailable.",
-        "enum": [
-          "completed",
-          "partial"
-        ],
-        "type": "string"
-      },
-      "target": {
-        "description": "Canonical audited target.",
-        "type": "string"
-      },
-      "total": {
-        "description": "Total findings produced before response truncation.",
-        "minimum": 0,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "target",
-      "kind",
-      "score",
-      "grade",
-      "counts",
-      "total",
-      "returnedFindings",
-      "findingsTruncated",
-      "passingChecks",
-      "findings"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "executionComplete": {
-        "const": false,
-        "description": "False until the entire audit result is ready for delivery.",
-        "type": "boolean"
-      },
-      "jobId": {
-        "description": "Opaque temporary job identifier bound to this account, tool and MCP surface.",
-        "pattern": "^mj_[A-Za-z0-9_-]{32}$",
-        "type": "string"
-      },
-      "nextAction": {
-        "const": "poll_same_tool",
-        "description": "Call this same tool again with pollArguments.",
-        "type": "string"
-      },
-      "pollArguments": {
-        "additionalProperties": false,
-        "description": "Arguments for retrieving this existing audit without starting another scan.",
-        "properties": {
-          "jobId": {
-            "description": "The same opaque audit job identifier.",
-            "pattern": "^mj_[A-Za-z0-9_-]{32}$",
-            "type": "string"
-          }
-        },
-        "required": [
-          "jobId"
-        ],
-        "type": "object"
-      },
-      "retryAfterMs": {
-        "description": "Suggested delay in milliseconds before polling this job again.",
-        "minimum": 0,
-        "type": "integer"
-      },
-      "status": {
-        "const": "running",
-        "description": "The audit is still executing or completing durable delivery.",
-        "type": "string"
-      }
-    },
-    "required": [
-      "status",
-      "jobId",
-      "executionComplete",
-      "nextAction",
-      "pollArguments",
-      "retryAfterMs"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "auditExecuted": {
-        "const": false,
-        "description": "This request did not execute a new audit.",
-        "type": "boolean"
-      },
-      "reason": {
-        "description": "The recoverable job request prerequisite.",
-        "enum": [
-          "audit_job_busy",
-          "audit_job_unavailable",
-          "audit_job_argument_mismatch",
-          "audit_job_invalid_arguments"
-        ],
-        "type": "string"
-      },
-      "status": {
-        "const": "action_required",
-        "description": "This request did not start a new audit.",
-        "type": "string"
-      },
-      "usageConsumed": {
-        "const": false,
-        "description": "This request did not consume additional audit allowance.",
-        "type": "boolean"
-      }
-    },
-    "required": [
-      "status",
-      "reason",
-      "auditExecuted",
-      "usageConsumed"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "oneOf": [
+      {
+        "additionalProperties": true,
+        "properties": {
+          "auditDetails": {
+            "additionalProperties": true,
+            "description": "Complete available scope, check states and measurement evidence; unmeasured checks are not passes.",
+            "type": "object"
+          },
+          "counts": {
+            "additionalProperties": false,
+            "description": "Finding totals grouped by normalized severity.",
+            "properties": {
+              "critical": {
+                "description": "Number of critical findings.",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "high": {
+                "description": "Number of high-severity findings.",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "info": {
+                "description": "Number of informational findings.",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "low": {
+                "description": "Number of low-severity findings.",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "medium": {
+                "description": "Number of medium-severity findings.",
+                "minimum": 0,
+                "type": "integer"
+              }
+            },
+            "required": [
+              "critical",
+              "high",
+              "medium",
+              "low",
+              "info"
+            ],
+            "type": "object"
+          },
+          "coverageStatus": {
+            "description": "Availability of measurements within the requested methods and account scope; not a claim to test every possible website behavior.",
+            "enum": [
+              "measured",
+              "partial",
+              "unavailable",
+              "not_applicable"
+            ],
+            "type": "string"
+          },
+          "executionComplete": {
+            "description": "Whether all requested pillar runners returned. This is separate from measurement coverage.",
+            "type": "boolean"
+          },
+          "findings": {
+            "description": "Prioritized findings with evidence, impact, and remediation.",
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "category": {
+                  "description": "Stable audit category for grouping related findings.",
+                  "type": "string"
+                },
+                "evidence": {
+                  "description": "Bounded observation that supports the finding.",
+                  "type": "string"
+                },
+                "findingKey": {
+                  "description": "Deterministic pillar-scoped identity for before/after comparison.",
+                  "maxLength": 512,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "impact": {
+                  "description": "Why the finding matters to the audited website.",
+                  "type": "string"
+                },
+                "location": {
+                  "description": "Observed URL or path with credentials and query secrets removed, when available.",
+                  "type": "string"
+                },
+                "remediation": {
+                  "description": "Concrete recommended fix or mitigation.",
+                  "type": "string"
+                },
+                "severity": {
+                  "description": "Normalized finding severity: critical, high, medium, low, or info.",
+                  "type": "string"
+                },
+                "title": {
+                  "description": "Short human-readable finding title.",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "findingKey",
+                "severity",
+                "title",
+                "evidence",
+                "impact",
+                "remediation",
+                "category"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "findingsTruncated": {
+            "description": "True when additional findings exist outside this response.",
+            "type": "boolean"
+          },
+          "grade": {
+            "description": "Human-readable grade, or null when unavailable.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "kind": {
+            "description": "Audit pillar represented by this result.",
+            "type": "string"
+          },
+          "passingChecks": {
+            "description": "Number of checks that passed or reported protection.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "passingFindings": {
+            "description": "Positive observations retained with their complete evidence.",
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "category": {
+                  "description": "Stable audit category for grouping related findings.",
+                  "type": "string"
+                },
+                "evidence": {
+                  "description": "Bounded observation that supports the finding.",
+                  "type": "string"
+                },
+                "findingKey": {
+                  "description": "Deterministic pillar-scoped identity for before/after comparison.",
+                  "maxLength": 512,
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "impact": {
+                  "description": "Why the finding matters to the audited website.",
+                  "type": "string"
+                },
+                "location": {
+                  "description": "Observed URL or path with credentials and query secrets removed, when available.",
+                  "type": "string"
+                },
+                "remediation": {
+                  "description": "Concrete recommended fix or mitigation.",
+                  "type": "string"
+                },
+                "severity": {
+                  "description": "Normalized finding severity: critical, high, medium, low, or info.",
+                  "type": "string"
+                },
+                "title": {
+                  "description": "Short human-readable finding title.",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "findingKey",
+                "severity",
+                "title",
+                "evidence",
+                "impact",
+                "remediation",
+                "category"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "returnedFindings": {
+            "description": "Number of findings included in this response.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "score": {
+            "description": "Measured score from 0 to 100, or null when unavailable.",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "status": {
+            "description": "Completed when requested measurements are available; partial when a requested runner or measurement is unavailable.",
+            "enum": [
+              "completed",
+              "partial"
+            ],
+            "type": "string"
+          },
+          "target": {
+            "description": "Canonical audited target.",
+            "type": "string"
+          },
+          "total": {
+            "description": "Total findings produced before response truncation.",
+            "minimum": 0,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "target",
+          "kind",
+          "score",
+          "grade",
+          "counts",
+          "total",
+          "returnedFindings",
+          "findingsTruncated",
+          "passingChecks",
+          "findings"
+        ],
+        "type": "object"
+      },
+      {
+        "additionalProperties": false,
+        "properties": {
+          "executionComplete": {
+            "const": false,
+            "description": "False until the entire audit result is ready for delivery.",
+            "type": "boolean"
+          },
+          "jobId": {
+            "description": "Opaque temporary job identifier bound to this account, tool and MCP surface.",
+            "pattern": "^mj_[A-Za-z0-9_-]{32}$",
+            "type": "string"
+          },
+          "nextAction": {
+            "const": "poll_same_tool",
+            "description": "Call this same tool again with pollArguments.",
+            "type": "string"
+          },
+          "pollArguments": {
+            "additionalProperties": false,
+            "description": "Arguments for retrieving this existing audit without starting another scan.",
+            "properties": {
+              "jobId": {
+                "description": "The same opaque audit job identifier.",
+                "pattern": "^mj_[A-Za-z0-9_-]{32}$",
+                "type": "string"
+              }
+            },
+            "required": [
+              "jobId"
+            ],
+            "type": "object"
+          },
+          "retryAfterMs": {
+            "description": "Suggested delay in milliseconds before polling this job again.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "status": {
+            "const": "running",
+            "description": "The audit is still executing or completing durable delivery.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "status",
+          "jobId",
+          "executionComplete",
+          "nextAction",
+          "pollArguments",
+          "retryAfterMs"
+        ],
+        "type": "object"
+      },
+      {
+        "additionalProperties": false,
+        "properties": {
+          "auditExecuted": {
+            "const": false,
+            "description": "This request did not execute a new audit.",
+            "type": "boolean"
+          },
+          "reason": {
+            "description": "The recoverable job request prerequisite.",
+            "enum": [
+              "audit_job_busy",
+              "audit_job_unavailable",
+              "audit_job_argument_mismatch",
+              "audit_job_invalid_arguments"
+            ],
+            "type": "string"
+          },
+          "status": {
+            "const": "action_required",
+            "description": "This request did not start a new audit.",
+            "type": "string"
+          },
+          "usageConsumed": {
+            "const": false,
+            "description": "This request did not consume additional audit allowance.",
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "status",
+          "reason",
+          "auditExecuted",
+          "usageConsumed"
+        ],
+        "type": "object"
+      }
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "auditExecuted": {
+        "const": false,
+        "type": "boolean"
+      },
+      "reason": {
+        "enum": [
+          "entitlement_required",
+          "target_verification_required",
+          "target_reverification_required",
+          "verification_scope_required",
+          "usage_limit_reached",
+          "authorization_consent_required"
+        ],
+        "type": "string"
+      },
+      "status": {
+        "const": "action_required",
+        "type": "string"
+      },
+      "usageConsumed": {
+        "const": false,
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "status",
+      "reason",
+      "auditExecuted",
+      "usageConsumed"
+    ],
+    "type": "object"
+  }
+]
  4. Changed7 schema fields changed
    • addedInput schema / anyOf
      Added value: +[
+  {
+    "required": [
+      "target"
+    ]
+  },
+  {
+    "maxProperties": 1,
+    "required": [
+      "jobId"
+    ]
+  }
+]
    • addedInput schema / properties / jobId
      Added value: +{
+  "description": "Resume an existing audit by polling this same tool with its returned jobId. Prefer jobId alone; if repeating other arguments, supply every original argument unchanged. Never invent a jobId.",
+  "pattern": "^mj_[A-Za-z0-9_-]{32}$",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "target"
-]
    • removedOutput schema / additionalProperties
      Removed value: -true
    • addedOutput schema / oneOf
      Added value: +[
+  {
+    "additionalProperties": true,
+    "properties": {
+      "auditDetails": {
+        "additionalProperties": true,
+        "description": "Complete available scope, check states and measurement evidence; unmeasured checks are not passes.",
+        "type": "object"
+      },
+      "counts": {
+        "additionalProperties": false,
+        "description": "Finding totals grouped by normalized severity.",
+        "properties": {
+          "critical": {
+            "description": "Number of critical findings.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "high": {
+            "description": "Number of high-severity findings.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "info": {
+            "description": "Number of informational findings.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "low": {
+            "description": "Number of low-severity findings.",
+            "minimum": 0,
+            "type": "integer"
+          },
+          "medium": {
+            "description": "Number of medium-severity findings.",
+            "minimum": 0,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "critical",
+          "high",
+          "medium",
+          "low",
+          "info"
+        ],
+        "type": "object"
+      },
+      "coverageStatus": {
+        "description": "Availability of measurements within the requested methods and account scope; not a claim to test every possible website behavior.",
+        "enum": [
+          "measured",
+          "partial",
+          "unavailable",
+          "not_applicable"
+        ],
+        "type": "string"
+      },
+      "executionComplete": {
+        "description": "Whether all requested pillar runners returned. This is separate from measurement coverage.",
+        "type": "boolean"
+      },
+      "findings": {
+        "description": "Prioritized findings with evidence, impact, and remediation.",
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "category": {
+              "description": "Stable audit category for grouping related findings.",
+              "type": "string"
+            },
+            "evidence": {
+              "description": "Bounded observation that supports the finding.",
+              "type": "string"
+            },
+            "findingKey": {
+              "description": "Deterministic pillar-scoped identity for before/after comparison.",
+              "maxLength": 512,
+              "minLength": 1,
+              "type": "string"
+            },
+            "impact": {
+              "description": "Why the finding matters to the audited website.",
+              "type": "string"
+            },
+            "location": {
+              "description": "Observed URL or path with credentials and query secrets removed, when available.",
+              "type": "string"
+            },
+            "remediation": {
+              "description": "Concrete recommended fix or mitigation.",
+              "type": "string"
+            },
+            "severity": {
+              "description": "Normalized finding severity: critical, high, medium, low, or info.",
+              "type": "string"
+            },
+            "title": {
+              "description": "Short human-readable finding title.",
+              "type": "string"
+            }
+          },
+          "required": [
+            "findingKey",
+            "severity",
+            "title",
+            "evidence",
+            "impact",
+            "remediation",
+            "category"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "findingsTruncated": {
+        "description": "True when additional findings exist outside this response.",
+        "type": "boolean"
+      },
+      "grade": {
+        "description": "Human-readable grade, or null when unavailable.",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "kind": {
+        "description": "Audit pillar represented by this result.",
+        "type": "string"
+      },
+      "passingChecks": {
+        "description": "Number of checks that passed or reported protection.",
+        "minimum": 0,
+        "type": "integer"
+      },
+      "passingFindings": {
+        "description": "Positive observations retained with their complete evidence.",
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "category": {
+              "description": "Stable audit category for grouping related findings.",
+              "type": "string"
+            },
+            "evidence": {
+              "description": "Bounded observation that supports the finding.",
+              "type": "string"
+            },
+            "findingKey": {
+              "description": "Deterministic pillar-scoped identity for before/after comparison.",
+              "maxLength": 512,
+              "minLength": 1,
+              "type": "string"
+            },
+            "impact": {
+              "description": "Why the finding matters to the audited website.",
+              "type": "string"
+            },
+            "location": {
+              "description": "Observed URL or path with credentials and query secrets removed, when available.",
+              "type": "string"
+            },
+            "remediation": {
+              "description": "Concrete recommended fix or mitigation.",
+              "type": "string"
+            },
+            "severity": {
+              "description": "Normalized finding severity: critical, high, medium, low, or info.",
+              "type": "string"
+            },
+            "title": {
+              "description": "Short human-readable finding title.",
+              "type": "string"
+            }
+          },
+          "required": [
+            "findingKey",
+            "severity",
+            "title",
+            "evidence",
+            "impact",
+            "remediation",
+            "category"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "returnedFindings": {
+        "description": "Number of findings included in this response.",
+        "minimum": 0,
+        "type": "integer"
+      },
+      "score": {
+        "description": "Measured score from 0 to 100, or null when unavailable.",
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "status": {
+        "description": "Completed when requested measurements are available; partial when a requested runner or measurement is unavailable.",
+        "enum": [
+          "completed",
+          "partial"
+        ],
+        "type": "string"
+      },
+      "target": {
+        "description": "Canonical audited target.",
+        "type": "string"
+      },
+      "total": {
+        "description": "Total findings produced before response truncation.",
+        "minimum": 0,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "target",
+      "kind",
+      "score",
+      "grade",
+      "counts",
+      "total",
+      "returnedFindings",
+      "findingsTruncated",
+      "passingChecks",
+      "findings"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "executionComplete": {
+        "const": false,
+        "description": "False until the entire audit result is ready for delivery.",
+        "type": "boolean"
+      },
+      "jobId": {
+        "description": "Opaque temporary job identifier bound to this account, tool and MCP surface.",
+        "pattern": "^mj_[A-Za-z0-9_-]{32}$",
+        "type": "string"
+      },
+      "nextAction": {
+        "const": "poll_same_tool",
+        "description": "Call this same tool again with pollArguments.",
+        "type": "string"
+      },
+      "pollArguments": {
+        "additionalProperties": false,
+        "description": "Arguments for retrieving this existing audit without starting another scan.",
+        "properties": {
+          "jobId": {
+            "description": "The same opaque audit job identifier.",
+            "pattern": "^mj_[A-Za-z0-9_-]{32}$",
+            "type": "string"
+          }
+        },
+        "required": [
+          "jobId"
+        ],
+        "type": "object"
+      },
+      "retryAfterMs": {
+        "description": "Suggested delay in milliseconds before polling this job again.",
+        "minimum": 0,
+        "type": "integer"
+      },
+      "status": {
+        "const": "running",
+        "description": "The audit is still executing or completing durable delivery.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "status",
+      "jobId",
+      "executionComplete",
+      "nextAction",
+      "pollArguments",
+      "retryAfterMs"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "auditExecuted": {
+        "const": false,
+        "description": "This request did not execute a new audit.",
+        "type": "boolean"
+      },
+      "reason": {
+        "description": "The recoverable job request prerequisite.",
+        "enum": [
+          "audit_job_busy",
+          "audit_job_unavailable",
+          "audit_job_argument_mismatch",
+          "audit_job_invalid_arguments"
+        ],
+        "type": "string"
+      },
+      "status": {
+        "const": "action_required",
+        "description": "This request did not start a new audit.",
+        "type": "string"
+      },
+      "usageConsumed": {
+        "const": false,
+        "description": "This request did not consume additional audit allowance.",
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "status",
+      "reason",
+      "auditExecuted",
+      "usageConsumed"
+    ],
+    "type": "object"
+  }
+]
    • removedOutput schema / properties
      Removed value: -{
-  "auditDetails": {
-    "additionalProperties": true,
-    "description": "Complete available scope, check states and measurement evidence; unmeasured checks are not passes.",
-    "type": "object"
-  },
-  "counts": {
-    "additionalProperties": false,
-    "description": "Finding totals grouped by normalized severity.",
-    "properties": {
-      "critical": {
-        "description": "Number of critical findings.",
-        "minimum": 0,
-        "type": "integer"
-      },
-      "high": {
-        "description": "Number of high-severity findings.",
-        "minimum": 0,
-        "type": "integer"
-      },
-      "info": {
-        "description": "Number of informational findings.",
-        "minimum": 0,
-        "type": "integer"
-      },
-      "low": {
-        "description": "Number of low-severity findings.",
-        "minimum": 0,
-        "type": "integer"
-      },
-      "medium": {
-        "description": "Number of medium-severity findings.",
-        "minimum": 0,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "critical",
-      "high",
-      "medium",
-      "low",
-      "info"
-    ],
-    "type": "object"
-  },
-  "coverageStatus": {
-    "description": "Availability of measurements within the requested methods and account scope; not a claim to test every possible website behavior.",
-    "enum": [
-      "measured",
-      "partial",
-      "unavailable",
-      "not_applicable"
-    ],
-    "type": "string"
-  },
-  "executionComplete": {
-    "description": "Whether all requested pillar runners returned. This is separate from measurement coverage.",
-    "type": "boolean"
-  },
-  "findings": {
-    "description": "Prioritized findings with evidence, impact, and remediation.",
-    "items": {
-      "additionalProperties": false,
-      "properties": {
-        "category": {
-          "description": "Stable audit category for grouping related findings.",
-          "type": "string"
-        },
-        "evidence": {
-          "description": "Bounded observation that supports the finding.",
-          "type": "string"
-        },
-        "findingKey": {
-          "description": "Deterministic pillar-scoped identity for before/after comparison.",
-          "maxLength": 512,
-          "minLength": 1,
-          "type": "string"
-        },
-        "impact": {
-          "description": "Why the finding matters to the audited website.",
-          "type": "string"
-        },
-        "location": {
-          "description": "Observed URL or path with credentials and query secrets removed, when available.",
-          "type": "string"
-        },
-        "remediation": {
-          "description": "Concrete recommended fix or mitigation.",
-          "type": "string"
-        },
-        "severity": {
-          "description": "Normalized finding severity: critical, high, medium, low, or info.",
-          "type": "string"
-        },
-        "title": {
-          "description": "Short human-readable finding title.",
-          "type": "string"
-        }
-      },
-      "required": [
-        "findingKey",
-        "severity",
-        "title",
-        "evidence",
-        "impact",
-        "remediation",
-        "category"
-      ],
-      "type": "object"
-    },
-    "type": "array"
-  },
-  "findingsTruncated": {
-    "description": "True when additional findings exist outside this response.",
-    "type": "boolean"
-  },
-  "grade": {
-    "description": "Human-readable grade, or null when unavailable.",
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  "kind": {
-    "description": "Audit pillar represented by this result.",
-    "type": "string"
-  },
-  "passingChecks": {
-    "description": "Number of checks that passed or reported protection.",
-    "minimum": 0,
-    "type": "integer"
-  },
-  "passingFindings": {
-    "description": "Positive observations retained with their complete evidence.",
-    "items": {
-      "additionalProperties": false,
-      "properties": {
-        "category": {
-          "description": "Stable audit category for grouping related findings.",
-          "type": "string"
-        },
-        "evidence": {
-          "description": "Bounded observation that supports the finding.",
-          "type": "string"
-        },
-        "findingKey": {
-          "description": "Deterministic pillar-scoped identity for before/after comparison.",
-          "maxLength": 512,
-          "minLength": 1,
-          "type": "string"
-        },
-        "impact": {
-          "description": "Why the finding matters to the audited website.",
-          "type": "string"
-        },
-        "location": {
-          "description": "Observed URL or path with credentials and query secrets removed, when available.",
-          "type": "string"
-        },
-        "remediation": {
-          "description": "Concrete recommended fix or mitigation.",
-          "type": "string"
-        },
-        "severity": {
-          "description": "Normalized finding severity: critical, high, medium, low, or info.",
-          "type": "string"
-        },
-        "title": {
-          "description": "Short human-readable finding title.",
-          "type": "string"
-        }
-      },
-      "required": [
-        "findingKey",
-        "severity",
-        "title",
-        "evidence",
-        "impact",
-        "remediation",
-        "category"
-      ],
-      "type": "object"
-    },
-    "type": "array"
-  },
-  "returnedFindings": {
-    "description": "Number of findings included in this response.",
-    "minimum": 0,
-    "type": "integer"
-  },
-  "score": {
-    "description": "Measured score from 0 to 100, or null when unavailable.",
-    "type": [
-      "number",
-      "null"
-    ]
-  },
-  "status": {
-    "description": "Completed when requested measurements are available; partial when a requested runner or measurement is unavailable.",
-    "enum": [
-      "completed",
-      "partial"
-    ],
-    "type": "string"
-  },
-  "target": {
-    "description": "Canonical audited target.",
-    "type": "string"
-  },
-  "total": {
-    "description": "Total findings produced before response truncation.",
-    "minimum": 0,
-    "type": "integer"
-  }
-}
    • removedOutput schema / required
      Removed value: -[
-  "target",
-  "kind",
-  "score",
-  "grade",
-  "counts",
-  "total",
-  "returnedFindings",
-  "findingsTruncated",
-  "passingChecks",
-  "findings"
-]
  5. Changed5 schema fields changed
    • changedOutput schema / properties / auditDetails / description
      Previous value: -"Bounded assessment scope, check states and available measurement evidence; unmeasured checks are not passes."New value: +"Complete available scope, check states and measurement evidence; unmeasured checks are not passes."
    • addedOutput schema / properties / coverageStatus
      Added value: +{
+  "description": "Availability of measurements within the requested methods and account scope; not a claim to test every possible website behavior.",
+  "enum": [
+    "measured",
+    "partial",
+    "unavailable",
+    "not_applicable"
+  ],
+  "type": "string"
+}
    • addedOutput schema / properties / executionComplete
      Added value: +{
+  "description": "Whether all requested pillar runners returned. This is separate from measurement coverage.",
+  "type": "boolean"
+}
    • addedOutput schema / properties / passingFindings
      Added value: +{
+  "description": "Positive observations retained with their complete evidence.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "category": {
+        "description": "Stable audit category for grouping related findings.",
+        "type": "string"
+      },
+      "evidence": {
+        "description": "Bounded observation that supports the finding.",
+        "type": "string"
+      },
+      "findingKey": {
+        "description": "Deterministic pillar-scoped identity for before/after comparison.",
+        "maxLength": 512,
+        "minLength": 1,
+        "type": "string"
+      },
+      "impact": {
+        "description": "Why the finding matters to the audited website.",
+        "type": "string"
+      },
+      "location": {
+        "description": "Observed URL or path with credentials and query secrets removed, when available.",
+        "type": "string"
+      },
+      "remediation": {
+        "description": "Concrete recommended fix or mitigation.",
+        "type": "string"
+      },
+      "severity": {
+        "description": "Normalized finding severity: critical, high, medium, low, or info.",
+        "type": "string"
+      },
+      "title": {
+        "description": "Short human-readable finding title.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "findingKey",
+      "severity",
+      "title",
+      "evidence",
+      "impact",
+      "remediation",
+      "category"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / status
      Added value: +{
+  "description": "Completed when requested measurements are available; partial when a requested runner or measurement is unavailable.",
+  "enum": [
+    "completed",
+    "partial"
+  ],
+  "type": "string"
+}
  6. Changed2 schema fields changed
    • addedOutput schema / properties / auditDetails
      Added value: +{
+  "additionalProperties": true,
+  "description": "Bounded assessment scope, check states and available measurement evidence; unmeasured checks are not passes.",
+  "type": "object"
+}
    • addedOutput schema / properties / findings / items / properties / location
      Added value: +{
+  "description": "Observed URL or path with credentials and query secrets removed, when available.",
+  "type": "string"
+}
  7. First observed

TDQS

A4.6/5.0
Behavior5/5

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

The description reveals important behavioral traits beyond the annotations: audits can be asynchronous, may return status running with jobId, and polling reuses the same audit without consuming more quota. It explicitly instructs clients not to treat running as completed and not to launch a replacement audit. This is far more transparency than the sparse annotations provide.

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 first sentence front-loads the tool's purpose and audit scope, and the following polling instructions are dense but relevant. Some of the polling guidance partially repeats the schema's jobId description, which prevents a perfect score, but no sentence is wasted.

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

Completeness5/5

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

The description covers the full async lifecycle: starting, polling, waiting on retryAfterMs, preserving quota, and avoiding duplicate audits. Since an output schema exists, the description does not need to explain return values in detail. For a three-parameter tool with a rich schema, this is complete.

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

Parameters4/5

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

The schema already covers all parameters with descriptions, including detailed jobId semantics, so the baseline is 3. The description adds value by clarifying the role split: target starts an audit while jobId polls a running one, and pollArguments must be copied unchanged. This role distinction is not fully explicit in the target parameter's schema description.

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

Purpose5/5

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

The description identifies a specific resource and scope: a 'Static WCAG 2.2 accessibility audit from the DOM' with a concrete list of checkable areas (alt text, form labels, landmarks, duplicate ids, iframe titles). This clearly differentiates it from sibling audit tools like audit_security, audit_performance, and audit_seo. The outcome, 'returns violations with fixes,' is also explicit.

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

Usage Guidelines4/5

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

The description gives a clear operational procedure: supply a target to start, or a jobId to poll; handle a running status by waiting retryAfterMs and reusing pollArguments unchanged. It also warns against starting a replacement audit while one is running. It does not explicitly contrast with the sibling audit tools, but the accessibility scope makes the intended usage clear.

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

All Sitelemetry toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources