ALPNAI — Agent Performance Tools

Quality Gate

check_agent_quality

Read-onlyIdempotent

Check whether a candidate agent workflow regresses before replacing the baseline. Supply baseline and candidate attempts on matching task IDs with client-provided success labels and costs. Returns observed success rates, task-set matching, sample-size, success, latency and cost gates, plus a decision such as collect_more_data, quality_regression or candidate_for_controlled_trial. Optional thresholds use config. It evaluates the recorded labels, not the correctness of answers or future performance. Free calculation; requires an active ALPNAI agent key; no payment or automatic deployment.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`runs`	Yes
`config`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`config`	Yes
`workflows`	Yes
`schema_version`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedSep 14, 2026

addedInput schema / description

Added value: +"Recorded attempts, not prompts or secrets. Identical rows count as separate attempts. All three analysis tools accept this same input. The runtime validator additionally enforces six-decimal micro-USD precision, the same task_id belonging to one workflow, one workflow when monthlyTasks is given, and UTF-16 length limits. HTTP body limit: 512000 UTF-8 bytes."

addedInput schema / properties / config / additionalProperties
```
Added value: +false
```

addedInput schema / properties / config / properties

Added value: +{
+  "maxP95LatencyMs": {
+    "maximum": 86400000000,
+    "minimum": 0,
+    "type": "number"
+  },
+  "maxSuccessRateDrop": {
+    "default": 0.02,
+    "maximum": 1,
+    "minimum": 0,
+    "type": "number"
+  },
+  "minSamples": {
+    "default": 30,
+    "maximum": 500,
+    "minimum": 2,
+    "type": "integer"
+  },
+  "minSuccessRate": {
+    "default": 0.95,
+    "maximum": 1,
+    "minimum": 0,
+    "type": "number"
+  },
+  "monthlyTasks": {
+    "description": "Baseline logical tasks launched per month; the engine requires exactly one workflow if supplied.",
+    "maximum": 1000000,
+    "minimum": 1,
+    "type": "integer"
+  }
+}

addedInput schema / properties / config / required
```
Added value: +[]
```
addedInput schema / properties / runs / items / additionalProperties
```
Added value: +false
```

addedInput schema / properties / runs / items / properties

Added value: +{
+  "cost_usd": {
+    "description": "USD cost of this attempt. At most six decimal places; the engine verifies whole micro-USD using floating-point tolerance. No multipleOf keyword is used, to avoid rejecting valid JSON decimals.",
+    "maximum": 10000,
+    "minimum": 0,
+    "type": "number"
+  },
+  "latency_ms": {
+    "description": "Recorded attempt duration in milliseconds; decimals are accepted. Omit if not measured.",
+    "maximum": 86400000,
+    "minimum": 0,
+    "type": "number"
+  },
+  "success": {
+    "type": "boolean"
+  },
+  "task_id": {
+    "description": "Nonempty, no control characters or surrounding whitespace. The engine additionally enforces at most 128 UTF-16 code units.",
+    "maxLength": 128,
+    "minLength": 1,
+    "pattern": "^(?!\\s)(?![\\s\\S]*\\s$)[^\\u0000-\\u001F\\u007F]+$",
+    "type": "string"
+  },
+  "variant": {
+    "enum": [
+      "baseline",
+      "candidate"
+    ],
+    "type": "string"
+  },
+  "workflow": {
+    "description": "Nonempty, no control characters or surrounding whitespace. The engine additionally enforces at most 80 UTF-16 code units.",
+    "maxLength": 80,
+    "minLength": 1,
+    "pattern": "^(?!\\s)(?![\\s\\S]*\\s$)[^\\u0000-\\u001F\\u007F]+$",
+    "type": "string"
+  }
+}

addedInput schema / properties / runs / items / required

Added value: +[
+  "task_id",
+  "workflow",
+  "variant",
+  "cost_usd",
+  "success"
+]

addedInput schema / title

Added value: +"ALPNAI recorded agent attempts"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "config": {
+      "additionalProperties": true,
+      "properties": {
+        "maxP95LatencyMs": {
+          "maximum": 86400000000,
+          "minimum": 0,
+          "type": "number"
+        },
+        "maxSuccessRateDrop": {
+          "default": 0.02,
+          "maximum": 1,
+          "minimum": 0,
+          "type": "number"
+        },
+        "minSamples": {
+          "default": 30,
+          "maximum": 500,
+          "minimum": 2,
+          "type": "integer"
+        },
+        "minSuccessRate": {
+          "default": 0.95,
+          "maximum": 1,
+          "minimum": 0,
+          "type": "number"
+        },
+        "monthlyTasks": {
+          "description": "Baseline logical tasks launched per month; the engine requires exactly one workflow if supplied.",
+          "maximum": 1000000,
+          "minimum": 1,
+          "type": "integer"
+        }
+      },
+      "required": [
+        "minSamples",
+        "minSuccessRate",
+        "maxSuccessRateDrop"
+      ],
+      "type": "object"
+    },
+    "schema_version": {
+      "const": "1.0.0",
+      "type": "string"
+    },
+    "workflows": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "automatic_deployment_authorized": {
+            "const": false,
+            "type": "boolean"
+          },
+          "baseline_success": {
+            "anyOf": [
+              {
+                "maximum": 1,
+                "minimum": 0,
+                "type": "number"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "candidate_success": {
+            "anyOf": [
+              {
+                "maximum": 1,
+                "minimum": 0,
+                "type": "number"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "comparison": {
+            "additionalProperties": true,
+            "properties": {
+              "baseline_only_tasks": {
+                "maximum": 1000,
+                "minimum": 0,
+                "type": "integer"
+              },
+              "candidate_only_tasks": {
+                "maximum": 1000,
+                "minimum": 0,
+                "type": "integer"
+              },
+              "matched_task_ids": {
+                "maximum": 1000,
+                "minimum": 0,
+                "type": "integer"
+              },
+              "same_task_set": {
+                "type": "boolean"
+              }
+            },
+            "required": [
+              "matched_task_ids",
+              "baseline_only_tasks",
+              "candidate_only_tasks",
+              "same_task_set"
+            ],
+            "type": "object"
+          },
+          "decision": {
+            "enum": [
+              "missing_comparison",
+              "collect_more_data",
+              "quality_regression",
+              "latency_data_required",
+              "latency_regression",
+              "no_economic_advantage",
+              "candidate_for_controlled_trial"
+            ],
+            "type": "string"
+          },
+          "gates": {
+            "additionalProperties": true,
+            "properties": {
+              "both_variants": {
+                "enum": [
+                  "pass",
+                  "fail",
+                  "unknown",
+                  "not_requested"
+                ],
+                "type": "string"
+              },
+              "experimental_bias_control": {
+                "const": "unknown",
+                "type": "string"
+              },
+              "lower_cost_per_successful_task": {
+                "enum": [
+                  "pass",
+                  "fail",
+                  "unknown",
+                  "not_requested"
+                ],
+                "type": "string"
+              },
+              "minimum_distinct_tasks_per_variant": {
+                "enum": [
+                  "pass",
+                  "fail",
+                  "unknown",
+                  "not_requested"
+                ],
+                "type": "string"
+              },
+              "observed_success_rate": {
+                "enum": [
+                  "pass",
+                  "fail",
+                  "unknown",
+                  "not_requested"
+                ],
+                "type": "string"
+              },
+              "recorded_latency": {
+                "enum": [
+                  "pass",
+                  "fail",
+                  "unknown",
+                  "not_requested"
+                ],
+                "type": "string"
+              },
+              "same_task_set": {
+                "enum": [
+                  "pass",
+                  "fail",
+                  "unknown",
+                  "not_requested"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "both_variants",
+              "minimum_distinct_tasks_per_variant",
+              "same_task_set",
+              "observed_success_rate",
+              "recorded_latency",
+              "lower_cost_per_successful_task",
+              "experimental_bias_control"
+            ],
+            "type": "object"
+          },
+          "workflow": {
+            "description": "Nonempty, no control characters or surrounding whitespace. The engine additionally enforces at most 80 UTF-16 code units.",
+            "maxLength": 80,
+            "minLength": 1,
+            "pattern": "^(?!\\s)(?![\\s\\S]*\\s$)[^\\u0000-\\u001F\\u007F]+$",
+            "type": "string"
+          }
+        },
+        "required": [
+          "workflow",
+          "comparison",
+          "gates",
+          "decision",
+          "baseline_success",
+          "candidate_success",
+          "automatic_deployment_authorized"
+        ],
+        "type": "object"
+      },
+      "maxItems": 1000,
+      "minItems": 1,
+      "type": "array"
+    }
+  },
+  "required": [
+    "schema_version",
+    "config",
+    "workflows"
+  ],
+  "type": "object"
+}

First observedSep 14, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already mark the tool read-only, idempotent, and non-destructive. The description adds substantial behavioral context beyond that: it evaluates recorded labels rather than correctness or future performance, has no payment or automatic deployment, requires an active key, and is free. No contradiction with annotations exists.

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 front-loaded with the main purpose, then flows from input, to output, to config, to caveats and access requirements. Every sentence carries distinct, necessary information with no filler or repetition.

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?

For a complex comparison tool with an output schema, the description covers input semantics, decision output types, optional config, key caveats, and authentication/payment constraints. Schema-level details like body limits and validation rules are already present, so the description does not need to repeat them.

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 description gives semantic roles to both parameters: 'runs' are baseline/candidate attempts with client-provided success labels and costs, and 'config' supplies optional thresholds. This compensates for the low schema coverage, though it does not enumerate every config field or required field within runs.

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 first sentence names a specific verb ('check'), the resource ('candidate agent workflow'), and the decision frame ('before replacing the baseline'). It also clarifies the tool's quality focus, which distinguishes it from latency and cost analysis siblings. This is unambiguous and actionable.

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 clearly states when to use it—before replacing a baseline—and what inputs to supply: baseline and candidate attempts on matching task IDs. It does not explicitly name sibling alternatives or when-not conditions, but the context is strong enough for an agent to select the tool appropriately.

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

All ALPNAI — Agent Performance Tools tools Inspect

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

Need Help?