Skip to main content
Glama
Sign In

Phare

by io.phare.mcp
OverviewDiscussionsAdmin

Get report

get_report
Read-onlyIdempotent

Get the availability, downtime, incident count, MTTR and MTBF of every monitor of the project and their aggregates, between two past dates up to 1 year apart, the last 30 days by default.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>"
    },
    "name": "get_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoEnd of the reporting window, defaults to now. Must be after `from` and not in the future, required when `from` is provided.
fromNoStart of the reporting window, defaults to 30 days ago. Must be in the past, required when `to` is provided.
project_idYesID of the project to act on, see whoami

Output Schema

NameRequiredDescriptionDefault
mtbfNoMean time between failures (MTBF) average for monitors with downtime, in seconds
mttrNoMean time to recovery (MTTR) average for monitors with downtime, in seconds
downtimeNoTotal downtime across all monitors in seconds
monitorsNoPer-monitor statistics for all monitors included in the report
availabilityNoMean monitor availability across the selected range, as a percentage
report_end_atNoEffective end of the generated report window
report_start_atNoEffective start of the generated report window
max_availabilityNoHighest monitor availability in the selected range, as a percentage
min_availabilityNoLowest monitor availability in the selected range, as a percentage
highest_incident_impactNoHighest impact level observed among incidents in the selected range

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "availability": {
+      "description": "Mean monitor availability across the selected range, as a percentage",
+      "examples": [
+        99.9634
+      ],
+      "format": "float",
+      "type": "number"
+    },
+    "downtime": {
+      "description": "Total downtime across all monitors in seconds",
+      "examples": [
+        2940
+      ],
+      "type": "integer"
+    },
+    "highest_incident_impact": {
+      "description": "Highest impact level observed among incidents in the selected range",
+      "enum": [
+        "unknown",
+        "operational",
+        "maintenance",
+        "degraded_performance",
+        "partial_outage",
+        "major_outage"
+      ],
+      "examples": [
+        "major_outage"
+      ],
+      "type": "string"
+    },
+    "max_availability": {
+      "description": "Highest monitor availability in the selected range, as a percentage",
+      "examples": [
+        100
+      ],
+      "format": "float",
+      "type": "number"
+    },
+    "min_availability": {
+      "description": "Lowest monitor availability in the selected range, as a percentage",
+      "examples": [
+        99.9125
+      ],
+      "format": "float",
+      "type": "number"
+    },
+    "monitors": {
+      "description": "Per-monitor statistics for all monitors included in the report",
+      "items": {
+        "properties": {
+          "availability": {
+            "description": "Availability for this monitor in the selected range, as a percentage",
+            "examples": [
+              99.944
+            ],
+            "format": "float",
+            "type": "number"
+          },
+          "downtime": {
+            "description": "Total downtime for this monitor in seconds",
+            "examples": [
+              1500
+            ],
+            "type": "integer"
+          },
+          "highest_incident_impact": {
+            "description": "Highest impact level observed for this monitor in the selected range",
+            "enum": [
+              "unknown",
+              "operational",
+              "maintenance",
+              "degraded_performance",
+              "partial_outage",
+              "major_outage"
+            ],
+            "examples": [
+              "major_outage"
+            ],
+            "type": "string"
+          },
+          "id": {
+            "description": "Monitor ID",
+            "examples": [
+              12
+            ],
+            "type": "integer"
+          },
+          "incident_count": {
+            "description": "Number of incidents affecting this monitor in the selected range",
+            "examples": [
+              2
+            ],
+            "type": "integer"
+          },
+          "incidents": {
+            "description": "Incidents that affected this monitor in the selected range",
+            "items": {
+              "properties": {
+                "created_at": {
+                  "description": "Date of creation for the entity",
+                  "format": "date-time",
+                  "type": "string"
+                },
+                "description": {
+                  "description": "Description of the error that caused the incident",
+                  "examples": [
+                    "The server answered with an unexpected status code: 503."
+                  ],
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "exclude_from_downtime": {
+                  "description": "Flag to exclude the incident from downtime calculations",
+                  "examples": [
+                    false
+                  ],
+                  "type": "boolean"
+                },
+                "id": {
+                  "examples": [
+                    1
+                  ],
+                  "type": "integer"
+                },
+                "impact": {
+                  "description": "Incident impact",
+                  "enum": [
+                    "unknown",
+                    "operational",
+                    "maintenance",
+                    "degraded_performance",
+                    "partial_outage",
+                    "major_outage"
+                  ],
+                  "type": "string"
+                },
+                "incident_at": {
+                  "description": "Date of incident confirmation, defaults to the current date on creation. Must be within the last year and no more than 10 minutes in the future.",
+                  "format": "date-time",
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "monitors": {
+                  "description": "List of monitors linked to the incident",
+                  "examples": [
+                    [
+                      1,
+                      2,
+                      3
+                    ]
+                  ],
+                  "items": {
+                    "type": "integer"
+                  },
+                  "type": "array"
+                },
+                "project_id": {
+                  "description": "Parent project ID",
+                  "examples": [
+                    1
+                  ],
+                  "type": "integer"
+                },
+                "recovery_at": {
+                  "description": "Date of incident recovery. Must be after `incident_at`, within the last year and no more than 10 minutes in the future. Cannot be removed once the incident is recovered.",
+                  "format": "date-time",
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "slug": {
+                  "description": "Incident unique slug name",
+                  "examples": [
+                    "APP-123"
+                  ],
+                  "type": "string"
+                },
+                "state": {
+                  "description": "Incident state",
+                  "enum": [
+                    "unknown",
+                    "investigating",
+                    "identified",
+                    "monitoring",
+                    "resolved"
+                  ],
+                  "type": "string"
+                },
+                "status": {
+                  "description": "Incident status",
+                  "enum": [
+                    "ongoing",
+                    "recovering",
+                    "recovered"
+                  ],
+                  "type": "string"
+                },
+                "tags": {
+                  "description": "Resource tags, made of lowercase letters, numbers, `.`, `_`, `:` and `-`. An organization can have up to 200 tags.",
+                  "items": {
+                    "examples": [
+                      "environment:production"
+                    ],
+                    "type": "string"
+                  },
+                  "type": [
+                    "array",
+                    "null"
+                  ]
+                },
+                "title": {
+                  "description": "Incident title",
+                  "examples": [
+                    "Service is not working as expected"
+                  ],
+                  "type": "string"
+                },
+                "type": {
+                  "description": "Incident type",
+                  "enum": [
+                    "monitor",
+                    "manual"
+                  ],
+                  "type": "string"
+                },
+                "updated_at": {
+                  "description": "Date of last update for the entity",
+                  "format": "date-time",
+                  "type": "string"
+                }
+              },
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "mtbf": {
+            "description": "Mean time between failures (MTBF) for this monitor, in seconds",
+            "examples": [
+              43200
+            ],
+            "type": [
+              "integer",
+              "null"
+            ]
+          },
+          "mttr": {
+            "description": "Mean time to recovery (MTTR) for this monitor, in seconds",
+            "examples": [
+              750
+            ],
+            "type": [
+              "integer",
+              "null"
+            ]
+          },
+          "name": {
+            "description": "Monitor name",
+            "examples": [
+              "Website"
+            ],
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "mtbf": {
+      "description": "Mean time between failures (MTBF) average for monitors with downtime, in seconds",
+      "examples": [
+        43200
+      ],
+      "format": "float",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "mttr": {
+      "description": "Mean time to recovery (MTTR) average for monitors with downtime, in seconds",
+      "examples": [
+        735
+      ],
+      "format": "float",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "report_end_at": {
+      "description": "Effective end of the generated report window",
+      "examples": [
+        "2026-04-30T23:59:59Z"
+      ],
+      "format": "date-time",
+      "type": "string"
+    },
+    "report_start_at": {
+      "description": "Effective start of the generated report window",
+      "examples": [
+        "2026-04-01T00:00:00Z"
+      ],
+      "format": "date-time",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile needs no restating. The description adds non-obvious behavior on top of that: an enforced maximum span of one year between the two dates and a 30-day default window, both of which are invisible in the annotations. That materially reduces the chance of a rejected call.

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

Conciseness5/5

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

A single sentence, front-loaded with the metrics returned before the scope and the window constraints. Every clause carries information - metrics, scope, date bounds, default - and there is no filler, hedging, or restatement of the title.

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

Completeness4/5

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

An output schema exists and the input schema is fully described, so the description need not explain return shapes or field meanings. It covers the remaining gaps (scope, window bounds, default range) well; only the absence of explicit sibling routing keeps it from being fully complete for a report tool sitting next to get_monitor_report.

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?

Schema coverage is 100%, so the baseline is 3 and the schema already documents the defaults and mutual requirement of from/to. The description still earns credit by stating the one-year maximum separation between the two dates, a constraint the schema never mentions, which is the kind of rule an agent would otherwise discover only through a failed call.

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?

"Get the availability, downtime, incident count, MTTR and MTBF of every monitor of the project and their aggregates" gives a specific verb, an enumerated set of metrics, and an explicit scope (all monitors of a project plus aggregates). This implicitly separates it from the sibling get_monitor_report, which covers a single monitor, but that sibling is never named, so an agent must infer the distinction.

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?

The description supplies real usage constraints: both dates must be in the past, the window may span at most one year, and the default is the last 30 days. What it lacks is routing guidance - nothing says when to choose this project-wide report over get_monitor_report for one monitor, or how it relates to list_monitors.

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

All Phare toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources