OneLence

Compare sources

onelence_compare_sources

Read-onlyIdempotent

Two sources side by side for one window (visitors, conversions, conversion rate, observed revenue, Decision and signal state). Pass source ids or names from onelence_list_sources. It ranks nothing and is not a Decision.

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": {
      "a": "<a>",
      "b": "<b>"
    },
    "name": "onelence_compare_sources"
  }
}

Input Schema

Name	Required	Description
`a`	Yes
`b`	Yes
`end`	No	Window end, inclusive for a date. Defaults to now.
`site`	No	Site domain (e.g. example.com) or site id. Defaults to the workspace's newest active site.
`start`	No	Window start: a date (YYYY-MM-DD) or ISO 8601 date-time. Defaults to 30 days before end.

Output Schema

Name	Required	Description	Default
`a`	Yes
`b`	Yes
`note`	Yes
`site`	Yes
`title`	Yes
`object`	Yes
`window`	Yes
`metrics`	Yes
`summary`	Yes
`disposition`	Yes
`limitations`	Yes
`availability`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "a": {
+      "properties": {
+        "conversion_rate": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "conversions": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "decision": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "name": {
+          "type": "string"
+        },
+        "observed_revenue": {
+          "anyOf": [
+            {
+              "properties": {
+                "amount": {
+                  "type": "number"
+                },
+                "currency": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "amount",
+                "currency"
+              ],
+              "type": "object"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "signals": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "visitors": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": [
+        "name",
+        "visitors",
+        "conversions",
+        "conversion_rate",
+        "observed_revenue",
+        "decision",
+        "signals"
+      ],
+      "type": "object"
+    },
+    "availability": {
+      "enum": [
+        "available",
+        "partial",
+        "unavailable"
+      ],
+      "type": "string"
+    },
+    "b": {
+      "properties": {
+        "conversion_rate": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "conversions": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "decision": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "name": {
+          "type": "string"
+        },
+        "observed_revenue": {
+          "anyOf": [
+            {
+              "properties": {
+                "amount": {
+                  "type": "number"
+                },
+                "currency": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "amount",
+                "currency"
+              ],
+              "type": "object"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "signals": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "visitors": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": [
+        "name",
+        "visitors",
+        "conversions",
+        "conversion_rate",
+        "observed_revenue",
+        "decision",
+        "signals"
+      ],
+      "type": "object"
+    },
+    "disposition": {
+      "enum": [
+        "comparable",
+        "incomparable"
+      ],
+      "type": "string"
+    },
+    "limitations": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "metrics": {
+      "items": {
+        "properties": {
+          "a": {
+            "type": "string"
+          },
+          "b": {
+            "type": "string"
+          },
+          "delta": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "label": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "label",
+          "a",
+          "b",
+          "delta"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "note": {
+      "type": "string"
+    },
+    "object": {
+      "const": "source_comparison",
+      "type": "string"
+    },
+    "site": {
+      "properties": {
+        "domain": {
+          "type": "string"
+        },
+        "id": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "id",
+        "domain"
+      ],
+      "type": "object"
+    },
+    "summary": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "title": {
+      "type": "string"
+    },
+    "window": {
+      "properties": {
+        "end_exclusive": {
+          "type": "string"
+        },
+        "start": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "start",
+        "end_exclusive"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "object",
+    "site",
+    "disposition",
+    "availability",
+    "title",
+    "summary",
+    "window",
+    "a",
+    "b",
+    "metrics",
+    "limitations",
+    "note"
+  ],
+  "type": "object"
+}

First observedOct 4, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral context by defining the output shape (the compared metrics) and explicitly denying ranking or Decision semantics. It does not address what happens when a source id is invalid or how many windows can be compared.

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?

Two short sentences, zero padding, with the scope and compared dimensions front-loaded and the caveat about ranking placed where it prevents misreading. Every clause carries information an agent would otherwise have to infer.

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, so return-value documentation is not strictly required, and the annotations cover the safety profile. The description supplies the two missing required-parameter semantics and the scope constraint, though it could add edge-case behavior (unknown source, identical a/b) for full completeness.

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?

With 60% schema coverage, the two required parameters 'a' and 'b' have no schema descriptions at all; the description compensates by stating they take source ids or names sourced from onelence_list_sources. The remaining parameters (site, start, end) are already documented in the schema, so the description correctly does not repeat them.

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 names a specific verb (compare) and resource (two sources) and enumerates the compared dimensions: visitors, conversions, conversion rate, observed revenue, Decision and signal state. The closing clause ('ranks nothing and is not a Decision') separates it from ranking/decision siblings such as onelence_get_decision and onelence_list_decisions.

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?

It gives a clear positive condition — two sources side by side over exactly one window — and tells the agent where to get the identifiers (onelence_list_sources). It also rules out a mistaken expectation (no ranking). It stops short of explicitly naming the alternative to use for multi-source or ranked comparisons, e.g. onelence_get_breakdown.

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

All OneLence 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.