Skip to main content
Glama

run_inference_profile

Execute a diagnostic-only profiling window against a managed vLLM server to capture performance traces for audit and comparison without modifying server state.

Instructions

Run one diagnostic-only profile window against a managed vLLM server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
plan_tokenYes
expected_plan_idNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed68 schema fields changedv0.1.15
    • removedInput schema / properties / measurement_run_id
      Removed value: -{
      -  "description": "Successful compatible unprofiled inference run to link.",
      -  "maxLength": 200,
      -  "minLength": 1,
      -  "title": "Measurement Run Id",
      -  "type": "string"
      -}
    • addedInput schema / properties / plan_token
      Added value: +{
      +  "pattern": "^[0-9a-f]{64}$",
      +  "title": "Plan Token",
      +  "type": "string"
      +}
    • removedInput schema / properties / profiler
      Removed value: -{
      -  "enum": [
      -    "torch_profiler",
      -    "nsight_systems"
      -  ],
      -  "title": "Profiler",
      -  "type": "string"
      -}
    • removedInput schema / properties / scenario_name
      Removed value: -{
      -  "maxLength": 100,
      -  "minLength": 1,
      -  "title": "Scenario Name",
      -  "type": "string"
      -}
    • removedInput schema / properties / server_name
      Removed value: -{
      -  "maxLength": 100,
      -  "minLength": 1,
      -  "title": "Server Name",
      -  "type": "string"
      -}
    • removedInput schema / properties / timeout_seconds
      Removed value: -{
      -  "default": 300,
      -  "exclusiveMinimum": 0,
      -  "maximum": 86400,
      -  "title": "Timeout Seconds",
      -  "type": "number"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "server_name",
      -  "scenario_name",
      -  "profiler",
      -  "measurement_run_id"
      -]New value: +[
      +  "plan_token"
      +]
    • removedOutput schema / $defs / ConfigureInferenceRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "configure_inference",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "enum": [
      -        "configure_inference_server",
      -        "list_inference_configurations"
      -      ],
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "ConfigureInferenceRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / ConfigureWorkloadRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "context": {
      -      "anyOf": [
      -        {
      -          "$ref": "#/$defs/ConfigureWorkloadRecoveryContext"
      -        },
      -        {
      -          "type": "null"
      -        }
      -      ],
      -      "default": null
      -    },
      -    "kind": {
      -      "const": "configure_workload",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "configure_workload",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "ConfigureWorkloadRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / ConfigureWorkloadRecoveryContext
      Removed value: -{
      -  "additionalProperties": false,
      -  "description": "Typed arguments for the safe structured configuration recovery.",
      -  "properties": {
      -    "config_path": {
      -      "const": "flameox.toml",
      -      "default": "flameox.toml",
      -      "title": "Config Path",
      -      "type": "string"
      -    },
      -    "kind": {
      -      "const": "configure_workload",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "operation": {
      -      "const": "create",
      -      "default": "create",
      -      "title": "Operation",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "kind"
      -  ],
      -  "title": "ConfigureWorkloadRecoveryContext",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / DiscoverArtifactsRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "discover_artifacts",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "list_artifacts",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "DiscoverArtifactsRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / DiscoverRunsRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "discover_runs",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "list_runs",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "DiscoverRunsRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / DiscoverWorkflowsRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "discover_workflows",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "enum": [
      -        "list_declared_workflows",
      -        "get_declared_workflow"
      -      ],
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "DiscoverWorkflowsRecovery",
      -  "type": "object"
      -}
    • changedOutput schema / $defs / ErrorCode / enum
      Previous value: -[
      -  "INVALID_ARGUMENTS",
      -  "WORKSPACE_NOT_FOUND",
      -  "WORKSPACE_INVALID",
      -  "RUN_NOT_FOUND",
      -  "CAPABILITY_UNAVAILABLE",
      -  "INVALID_CAPTURE_PLAN",
      -  "EXECUTION_REFUSED",
      -  "PROCESS_FAILED",
      -  "PROCESS_TIMEOUT",
      -  "PROCESS_CANCELLED",
      -  "ARTIFACT_TOO_LARGE",
      -  "ARTIFACT_INTEGRITY_FAILED",
      -  "ARTIFACT_PARSE_FAILED",
      -  "EVIDENCE_SCHEMA_MISMATCH",
      -  "COMPARISON_INVALID",
      -  "QUERY_BUDGET_EXCEEDED",
      -  "STORAGE_QUOTA_EXCEEDED",
      -  "WRITE_LOCK_TIMEOUT",
      -  "SENSITIVE_ARTIFACT_REFUSED",
      -  "REVISION_CONFLICT",
      -  "STALE_CURSOR",
      -  "INTERNAL_ERROR"
      -]New value: +[
      +  "INVALID_ARGUMENTS",
      +  "WORKSPACE_NOT_FOUND",
      +  "WORKSPACE_INVALID",
      +  "RUN_NOT_FOUND",
      +  "CAPABILITY_UNAVAILABLE",
      +  "INVALID_CAPTURE_PLAN",
      +  "PLAN_ID_MISMATCH",
      +  "PLAN_TOKEN_UNKNOWN",
      +  "PLAN_TOKEN_EXPIRED",
      +  "PLAN_TOKEN_CONSUMED",
      +  "EXECUTION_REFUSED",
      +  "PROCESS_FAILED",
      +  "PROCESS_TIMEOUT",
      +  "PROCESS_CANCELLED",
      +  "ARTIFACT_TOO_LARGE",
      +  "ARTIFACT_NOT_FOUND",
      +  "ARTIFACT_INTEGRITY_FAILED",
      +  "ARTIFACT_PARSE_FAILED",
      +  "ADAPTER_INCOMPATIBLE",
      +  "EVIDENCE_SCHEMA_MISMATCH",
      +  "COMPARISON_INVALID",
      +  "QUERY_BUDGET_EXCEEDED",
      +  "STORAGE_QUOTA_EXCEEDED",
      +  "WRITE_LOCK_TIMEOUT",
      +  "LOCK_ORDER_VIOLATION",
      +  "SENSITIVE_ARTIFACT_REFUSED",
      +  "REVISION_CONFLICT",
      +  "STALE_CURSOR",
      +  "INTERNAL_ERROR"
      +]
    • removedOutput schema / $defs / ExtractPerfettoRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "context": {
      -      "anyOf": [
      -        {
      -          "$ref": "#/$defs/ExtractPerfettoRecoveryContext"
      -        },
      -        {
      -          "type": "null"
      -        }
      -      ],
      -      "default": null
      -    },
      -    "kind": {
      -      "const": "extract_perfetto",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "extract_perfetto",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": true,
      -      "default": true,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "ExtractPerfettoRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / ExtractPerfettoRecoveryContext
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "extract_perfetto",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "run_id": {
      -      "minLength": 1,
      -      "title": "Run Id",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "run_id"
      -  ],
      -  "title": "ExtractPerfettoRecoveryContext",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / FailurePayload / properties / schema_version
      Removed value: -{
      -  "const": 1,
      -  "title": "Schema Version",
      -  "type": "integer"
      -}
    • changedOutput schema / $defs / FailurePayload / required
      Previous value: -[
      -  "schema_version",
      -  "ok",
      -  "result",
      -  "error"
      -]New value: +[
      +  "ok",
      +  "result",
      +  "error"
      +]
    • removedOutput schema / $defs / ImportArtifactRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "import_artifact",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "import_artifact",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "ImportArtifactRecovery",
      -  "type": "object"
      -}
    • addedOutput schema / $defs / InferenceProfileCoverage
      Added value: +{
      +  "enum": [
      +    "complete",
      +    "partial",
      +    "unavailable"
      +  ],
      +  "title": "InferenceProfileCoverage",
      +  "type": "string"
      +}
    • removedOutput schema / $defs / InferenceProfilingResult
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "artifact_ids": {
      -      "items": {
      -        "type": "string"
      -      },
      -      "title": "Artifact Ids",
      -      "type": "array"
      -    },
      -    "artifact_run_ids": {
      -      "items": {
      -        "type": "string"
      -      },
      -      "title": "Artifact Run Ids",
      -      "type": "array"
      -    },
      -    "benchmark_exit_code": {
      -      "anyOf": [
      -        {
      -          "type": "integer"
      -        },
      -        {
      -          "type": "null"
      -        }
      -      ],
      -      "title": "Benchmark Exit Code"
      -    },
      -    "coverage": {
      -      "enum": [
      -        "complete",
      -        "partial",
      -        "unavailable"
      -      ],
      -      "title": "Coverage",
      -      "type": "string"
      -    },
      -    "extracted_run_ids": {
      -      "default": [],
      -      "items": {
      -        "type": "string"
      -      },
      -      "title": "Extracted Run Ids",
      -      "type": "array"
      -    },
      -    "limitations": {
      -      "items": {
      -        "type": "string"
      -      },
      -      "title": "Limitations",
      -      "type": "array"
      -    },
      -    "measurement_protocol_id": {
      -      "title": "Measurement Protocol Id",
      -      "type": "string"
      -    },
      -    "measurement_run_id": {
      -      "title": "Measurement Run Id",
      -      "type": "string"
      -    },
      -    "plan_id": {
      -      "title": "Plan Id",
      -      "type": "string"
      -    },
      -    "profiler": {
      -      "enum": [
      -        "torch_profiler",
      -        "nsight_systems"
      -      ],
      -      "title": "Profiler",
      -      "type": "string"
      -    },
      -    "run_id": {
      -      "title": "Run Id",
      -      "type": "string"
      -    },
      -    "scenario_name": {
      -      "title": "Scenario Name",
      -      "type": "string"
      -    },
      -    "schema_version": {
      -      "const": 1,
      -      "default": 1,
      -      "title": "Schema Version",
      -      "type": "integer"
      -    },
      -    "server_cleanup_complete": {
      -      "title": "Server Cleanup Complete",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "run_id",
      -    "plan_id",
      -    "measurement_protocol_id",
      -    "measurement_run_id",
      -    "scenario_name",
      -    "profiler",
      -    "benchmark_exit_code",
      -    "server_cleanup_complete",
      -    "artifact_ids",
      -    "artifact_run_ids",
      -    "coverage",
      -    "limitations"
      -  ],
      -  "title": "InferenceProfilingResult",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / InitializeWorkspaceRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "initialize_workspace",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "initialize_workspace",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "InitializeWorkspaceRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / InspectCapabilitiesRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "inspect_capabilities",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "list_capabilities",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "InspectCapabilitiesRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / InspectWorkloadConfigurationRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "inspect_workload_configuration",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "workload_configuration_status",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "InspectWorkloadConfigurationRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / ManualConfigurationRecoveryContext
      Removed value: -{
      -  "additionalProperties": false,
      -  "description": "Typed context for configuration that cannot be safely rewritten by MCP.",
      -  "properties": {
      -    "config_path": {
      -      "const": "flameox.toml",
      -      "default": "flameox.toml",
      -      "title": "Config Path",
      -      "type": "string"
      -    },
      -    "diagnostic": {
      -      "maxLength": 500,
      -      "title": "Diagnostic",
      -      "type": "string"
      -    },
      -    "kind": {
      -      "const": "manual_configuration",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "verification_tool": {
      -      "const": "workload_configuration_status",
      -      "default": "workload_configuration_status",
      -      "title": "Verification Tool",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "diagnostic"
      -  ],
      -  "title": "ManualConfigurationRecoveryContext",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / ManualRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "context": {
      -      "anyOf": [
      -        {
      -          "$ref": "#/$defs/ManualConfigurationRecoveryContext"
      -        },
      -        {
      -          "type": "null"
      -        }
      -      ],
      -      "default": null
      -    },
      -    "kind": {
      -      "const": "manual",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "default": null,
      -      "title": "Next Tool",
      -      "type": "null"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind"
      -  ],
      -  "title": "ManualRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / PrepareAdapterRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "prepare_adapter",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "prepare_adapter",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": true,
      -      "default": true,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "PrepareAdapterRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / PrepareWorkloadDependenciesRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "prepare_workload_dependencies",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "prepare_workload_dependencies",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": true,
      -      "default": true,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "PrepareWorkloadDependenciesRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / configure_inference
      Removed value: -"#/$defs/ConfigureInferenceRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / configure_workload
      Removed value: -"#/$defs/ConfigureWorkloadRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / discover_artifacts
      Removed value: -"#/$defs/DiscoverArtifactsRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / discover_runs
      Removed value: -"#/$defs/DiscoverRunsRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / discover_workflows
      Removed value: -"#/$defs/DiscoverWorkflowsRecovery"
    • addedOutput schema / $defs / RecoveryAction / discriminator / mapping / external
      Added value: +"#/$defs/RecoveryExternalAction"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / extract_perfetto
      Removed value: -"#/$defs/ExtractPerfettoRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / import_artifact
      Removed value: -"#/$defs/ImportArtifactRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / initialize_workspace
      Removed value: -"#/$defs/InitializeWorkspaceRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / inspect_capabilities
      Removed value: -"#/$defs/InspectCapabilitiesRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / inspect_workload_configuration
      Removed value: -"#/$defs/InspectWorkloadConfigurationRecovery"
    • changedOutput schema / $defs / RecoveryAction / discriminator / mapping / manual
      Previous value: -"#/$defs/ManualRecovery"New value: +"#/$defs/RecoveryManualAction"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / prepare_adapter
      Removed value: -"#/$defs/PrepareAdapterRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / prepare_workload_dependencies
      Removed value: -"#/$defs/PrepareWorkloadDependenciesRecovery"
    • changedOutput schema / $defs / RecoveryAction / discriminator / mapping / repeat_same_call
      Previous value: -"#/$defs/RepeatSameCallRecovery"New value: +"#/$defs/RetryRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / replan_capture
      Removed value: -"#/$defs/ReplanCaptureRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / replan_inference
      Removed value: -"#/$defs/ReplanInferenceRecovery"
    • removedOutput schema / $defs / RecoveryAction / discriminator / mapping / start_capability_setup
      Removed value: -"#/$defs/StartCapabilitySetupRecovery"
    • addedOutput schema / $defs / RecoveryAction / discriminator / mapping / tool
      Added value: +"#/$defs/RecoveryToolAction"
    • changedOutput schema / $defs / RecoveryAction / discriminator / mapping / wait_then_repeat
      Previous value: -"#/$defs/WaitThenRepeatRecovery"New value: +"#/$defs/RetryRecovery"
    • changedOutput schema / $defs / RecoveryAction / oneOf
      Previous value: -[
      -  {
      -    "$ref": "#/$defs/RepeatSameCallRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/WaitThenRepeatRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/ReplanCaptureRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/InitializeWorkspaceRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/ConfigureWorkloadRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/InspectWorkloadConfigurationRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/StartCapabilitySetupRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/PrepareAdapterRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/PrepareWorkloadDependenciesRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/InspectCapabilitiesRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/DiscoverWorkflowsRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/DiscoverRunsRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/DiscoverArtifactsRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/ImportArtifactRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/ExtractPerfettoRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/ConfigureInferenceRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/ReplanInferenceRecovery"
      -  },
      -  {
      -    "$ref": "#/$defs/ManualRecovery"
      -  }
      -]New value: +[
      +  {
      +    "$ref": "#/$defs/RetryRecovery"
      +  },
      +  {
      +    "$ref": "#/$defs/RecoveryToolAction"
      +  },
      +  {
      +    "$ref": "#/$defs/RecoveryManualAction"
      +  },
      +  {
      +    "$ref": "#/$defs/RecoveryExternalAction"
      +  }
      +]
    • addedOutput schema / $defs / RecoveryExternalAction
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "instruction": {
      +      "maxLength": 500,
      +      "minLength": 1,
      +      "title": "Instruction",
      +      "type": "string"
      +    },
      +    "kind": {
      +      "const": "external",
      +      "default": "external",
      +      "title": "Kind",
      +      "type": "string"
      +    },
      +    "retry_after_ms": {
      +      "default": null,
      +      "title": "Retry After Ms",
      +      "type": "null"
      +    },
      +    "safe_to_repeat_same_call": {
      +      "const": false,
      +      "default": false,
      +      "title": "Safe To Repeat Same Call",
      +      "type": "boolean"
      +    },
      +    "system": {
      +      "maxLength": 100,
      +      "minLength": 1,
      +      "title": "System",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "instruction",
      +    "system"
      +  ],
      +  "title": "RecoveryExternalAction",
      +  "type": "object"
      +}
    • addedOutput schema / $defs / RecoveryManualAction
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "instruction": {
      +      "maxLength": 500,
      +      "minLength": 1,
      +      "title": "Instruction",
      +      "type": "string"
      +    },
      +    "kind": {
      +      "const": "manual",
      +      "default": "manual",
      +      "title": "Kind",
      +      "type": "string"
      +    },
      +    "missing_arguments": {
      +      "default": [],
      +      "items": {
      +        "type": "string"
      +      },
      +      "title": "Missing Arguments",
      +      "type": "array"
      +    },
      +    "retry_after_ms": {
      +      "default": null,
      +      "title": "Retry After Ms",
      +      "type": "null"
      +    },
      +    "safe_to_repeat_same_call": {
      +      "const": false,
      +      "default": false,
      +      "title": "Safe To Repeat Same Call",
      +      "type": "boolean"
      +    }
      +  },
      +  "required": [
      +    "instruction"
      +  ],
      +  "title": "RecoveryManualAction",
      +  "type": "object"
      +}
    • addedOutput schema / $defs / RecoveryToolAction
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "One executable MCP recovery action with a concrete tool name.",
      +  "properties": {
      +    "arguments": {
      +      "additionalProperties": true,
      +      "title": "Arguments",
      +      "type": "object"
      +    },
      +    "kind": {
      +      "const": "tool",
      +      "default": "tool",
      +      "title": "Kind",
      +      "type": "string"
      +    },
      +    "retry_after_ms": {
      +      "default": null,
      +      "title": "Retry After Ms",
      +      "type": "null"
      +    },
      +    "safe_to_repeat_same_call": {
      +      "const": false,
      +      "default": false,
      +      "title": "Safe To Repeat Same Call",
      +      "type": "boolean"
      +    },
      +    "tool_name": {
      +      "$ref": "#/$defs/ToolName"
      +    }
      +  },
      +  "required": [
      +    "tool_name"
      +  ],
      +  "title": "RecoveryToolAction",
      +  "type": "object"
      +}
    • removedOutput schema / $defs / RepeatSameCallRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "repeat_same_call",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "default": null,
      -      "title": "Next Tool",
      -      "type": "null"
      -    },
      -    "retry_after_ms": {
      -      "minimum": 0,
      -      "title": "Retry After Ms",
      -      "type": "integer"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": true,
      -      "default": true,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "retry_after_ms"
      -  ],
      -  "title": "RepeatSameCallRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / ReplanCaptureRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "replan_capture",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "plan_capture",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "ReplanCaptureRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / ReplanInferenceRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "replan_inference",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "plan_inference_scenario",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": false,
      -      "default": false,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "ReplanInferenceRecovery",
      -  "type": "object"
      -}
    • addedOutput schema / $defs / RetryRecovery
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "kind": {
      +      "enum": [
      +        "repeat_same_call",
      +        "wait_then_repeat"
      +      ],
      +      "title": "Kind",
      +      "type": "string"
      +    },
      +    "retry_after_ms": {
      +      "minimum": 0,
      +      "title": "Retry After Ms",
      +      "type": "integer"
      +    },
      +    "safe_to_repeat_same_call": {
      +      "const": true,
      +      "default": true,
      +      "title": "Safe To Repeat Same Call",
      +      "type": "boolean"
      +    }
      +  },
      +  "required": [
      +    "kind",
      +    "retry_after_ms"
      +  ],
      +  "title": "RetryRecovery",
      +  "type": "object"
      +}
    • removedOutput schema / $defs / StartCapabilitySetupRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "start_capability_setup",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "const": "start_capability_setup",
      -      "title": "Next Tool",
      -      "type": "string"
      -    },
      -    "retry_after_ms": {
      -      "default": null,
      -      "title": "Retry After Ms",
      -      "type": "null"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": true,
      -      "default": true,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "next_tool"
      -  ],
      -  "title": "StartCapabilitySetupRecovery",
      -  "type": "object"
      -}
    • removedOutput schema / $defs / SuccessPayload_InferenceProfilingResult_ / properties / result / $ref
      Removed value: -"#/$defs/InferenceProfilingResult"
    • addedOutput schema / $defs / SuccessPayload_InferenceProfilingResult_ / properties / result / additionalProperties
      Added value: +false
    • addedOutput schema / $defs / SuccessPayload_InferenceProfilingResult_ / properties / result / properties
      Added value: +{
      +  "artifact_ids": {
      +    "items": {
      +      "type": "string"
      +    },
      +    "title": "Artifact Ids",
      +    "type": "array"
      +  },
      +  "artifact_run_ids": {
      +    "items": {
      +      "type": "string"
      +    },
      +    "title": "Artifact Run Ids",
      +    "type": "array"
      +  },
      +  "benchmark_exit_code": {
      +    "anyOf": [
      +      {
      +        "type": "integer"
      +      },
      +      {
      +        "type": "null"
      +      }
      +    ],
      +    "title": "Benchmark Exit Code"
      +  },
      +  "coverage": {
      +    "$ref": "#/$defs/InferenceProfileCoverage"
      +  },
      +  "export_duration_ns": {
      +    "anyOf": [
      +      {
      +        "type": "integer"
      +      },
      +      {
      +        "type": "null"
      +      }
      +    ],
      +    "title": "Export Duration Ns"
      +  },
      +  "extracted_run_ids": {
      +    "default": [],
      +    "items": {
      +      "type": "string"
      +    },
      +    "title": "Extracted Run Ids",
      +    "type": "array"
      +  },
      +  "finalization_duration_ns": {
      +    "title": "Finalization Duration Ns",
      +    "type": "integer"
      +  },
      +  "limitations": {
      +    "items": {
      +      "type": "string"
      +    },
      +    "title": "Limitations",
      +    "type": "array"
      +  },
      +  "measurement_protocol_id": {
      +    "title": "Measurement Protocol Id",
      +    "type": "string"
      +  },
      +  "measurement_run_id": {
      +    "title": "Measurement Run Id",
      +    "type": "string"
      +  },
      +  "plan_id": {
      +    "title": "Plan Id",
      +    "type": "string"
      +  },
      +  "profiler": {
      +    "$ref": "#/$defs/SupportedInferenceProfiler"
      +  },
      +  "run_id": {
      +    "title": "Run Id",
      +    "type": "string"
      +  },
      +  "scenario_name": {
      +    "title": "Scenario Name",
      +    "type": "string"
      +  },
      +  "server_cleanup_complete": {
      +    "title": "Server Cleanup Complete",
      +    "type": "boolean"
      +  },
      +  "symbol_resolution_duration_ns": {
      +    "anyOf": [
      +      {
      +        "type": "integer"
      +      },
      +      {
      +        "type": "null"
      +      }
      +    ],
      +    "title": "Symbol Resolution Duration Ns"
      +  },
      +  "symbol_resolution_status": {
      +    "anyOf": [
      +      {
      +        "const": "disabled",
      +        "type": "string"
      +      },
      +      {
      +        "type": "null"
      +      }
      +    ],
      +    "title": "Symbol Resolution Status"
      +  },
      +  "workload_duration_ns": {
      +    "anyOf": [
      +      {
      +        "type": "integer"
      +      },
      +      {
      +        "type": "null"
      +      }
      +    ],
      +    "title": "Workload Duration Ns"
      +  }
      +}
    • addedOutput schema / $defs / SuccessPayload_InferenceProfilingResult_ / properties / result / required
      Added value: +[
      +  "run_id",
      +  "plan_id",
      +  "measurement_protocol_id",
      +  "measurement_run_id",
      +  "scenario_name",
      +  "profiler",
      +  "benchmark_exit_code",
      +  "server_cleanup_complete",
      +  "artifact_ids",
      +  "artifact_run_ids",
      +  "workload_duration_ns",
      +  "finalization_duration_ns",
      +  "export_duration_ns",
      +  "symbol_resolution_status",
      +  "symbol_resolution_duration_ns",
      +  "coverage",
      +  "limitations"
      +]
    • addedOutput schema / $defs / SuccessPayload_InferenceProfilingResult_ / properties / result / title
      Added value: +"InferenceProfilingResult"
    • addedOutput schema / $defs / SuccessPayload_InferenceProfilingResult_ / properties / result / type
      Added value: +"object"
    • removedOutput schema / $defs / SuccessPayload_InferenceProfilingResult_ / properties / schema_version
      Removed value: -{
      -  "const": 1,
      -  "title": "Schema Version",
      -  "type": "integer"
      -}
    • changedOutput schema / $defs / SuccessPayload_InferenceProfilingResult_ / required
      Previous value: -[
      -  "schema_version",
      -  "ok",
      -  "result",
      -  "error"
      -]New value: +[
      +  "ok",
      +  "result",
      +  "error"
      +]
    • addedOutput schema / $defs / SupportedInferenceProfiler
      Added value: +{
      +  "enum": [
      +    "torch_profiler",
      +    "nsight_systems"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / $defs / ToolName
      Added value: +{
      +  "enum": [
      +    "initialize_workspace",
      +    "workload_configuration_status",
      +    "configure_workload",
      +    "list_capabilities",
      +    "start_capability_setup",
      +    "get_capability_setup",
      +    "prepare_adapter",
      +    "prepare_workload_dependencies",
      +    "list_declared_workflows",
      +    "get_declared_workflow",
      +    "plan_fault_experiment",
      +    "plan_capture",
      +    "start_detached_capture",
      +    "get_detached_capture",
      +    "rebuild_catalog",
      +    "list_runs",
      +    "list_artifacts",
      +    "preview_artifact",
      +    "get_native_viewer_plan",
      +    "import_artifact",
      +    "import_xctrace",
      +    "extract_perfetto",
      +    "extract_memray",
      +    "get_extraction",
      +    "extract_nsight_systems",
      +    "extract_nsight_compute",
      +    "extract_compute_sanitizer",
      +    "configure_inference_server",
      +    "list_inference_configurations",
      +    "plan_inference_scenario",
      +    "execute_reduction",
      +    "get_reduction",
      +    "analyze_memory",
      +    "analyze_nsight_compute"
      +  ],
      +  "title": "ToolName",
      +  "type": "string"
      +}
    • removedOutput schema / $defs / WaitThenRepeatRecovery
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "kind": {
      -      "const": "wait_then_repeat",
      -      "title": "Kind",
      -      "type": "string"
      -    },
      -    "next_tool": {
      -      "default": null,
      -      "title": "Next Tool",
      -      "type": "null"
      -    },
      -    "retry_after_ms": {
      -      "minimum": 0,
      -      "title": "Retry After Ms",
      -      "type": "integer"
      -    },
      -    "safe_to_repeat_same_call": {
      -      "const": true,
      -      "default": true,
      -      "title": "Safe To Repeat Same Call",
      -      "type": "boolean"
      -    }
      -  },
      -  "required": [
      -    "kind",
      -    "retry_after_ms"
      -  ],
      -  "title": "WaitThenRepeatRecovery",
      -  "type": "object"
      -}
  2. Addedv0.1.12

TDQS

C2.7/5.0
Behavior2/5

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

Annotations indicate readOnlyHint=false, idempotentHint=false, and destructiveHint=false, and the description adds only 'diagnostic-only' and 'one ... profile window.' It does not disclose what side effects occur on the managed vLLM server, whether it blocks until completion, or whether it creates artifacts or state. There is no contradiction with the annotations, but the behavioral burden is not fully met.

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?

The description is a single, front-loaded sentence with no filler words. Every part—'run,' 'one,' 'diagnostic-only,' 'profile window,' 'managed vLLM server'—carries meaning, making it highly scannable for an agent.

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

Completeness2/5

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

Even with an output schema present, the tool requires plan_token, and nothing explains what a plan token is, how to obtain it, or what expected_plan_id validates. The description does not define 'profile window' or mention the relationship to the planning workflow, so an agent would still have significant ambiguity in invoking it correctly.

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

Parameters1/5

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

Schema description coverage is 0%, and the description does not mention plan_token or expected_plan_id at all. An agent is left to infer that plan_token is a 64-hex token and expected_plan_id is a nullable sha256 identifier, but the description provides no semantic meaning, origin, or relationship between them.

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 uses a specific verb ('Run') and a specific resource ('one diagnostic-only profile window against a managed vLLM server'), so an agent can tell this executes a profile rather than plans or configures one. It distinguishes itself from siblings like plan_inference_profile and run_inference_scenario at a surface level via 'profile window' and 'diagnostic-only', but it does not explicitly name or contrast those alternatives.

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

Usage Guidelines2/5

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

The description gives no guidance on when to use this tool versus run_inference_scenario, plan_inference_profile, or other inference family tools. It also does not state that plan_token is likely produced by a planning step or that this should run after plan_inference_profile, leaving prerequisites and tool-selection context unstated.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/morluto/flameox'

If you have feedback or need assistance with the MCP directory API, please join our Discord server