Skip to main content
Glama
Sign In

DevTune MCP

by ai.devtune
OverviewDiscussionsAdmin

devtune_get_direct_lift

Read-onlyIdempotent

Get complete-population GA4 Direct traffic and resolver-owned AI-correlated lift classifications from fixed-window rollups, with bounded page details. Direct lift is correlated evidence, not attributed traffic, and is never added to measured referral totals.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "devtune_get_direct_lift"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageLimitNoMaximum pages returned with their classification windows (1-25). Defaults to 10; aggregate totals are not capped.
windowDaysNoFixed rolling window in days: 7, 30, or 90. Defaults to 30.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / windowDays / anyOf
      Previous value: -[
-  {
-    "enum": [
-      "7",
-      "30",
-      "90"
-    ],
-    "type": "string"
-  },
-  {
-    "enum": [
-      7,
-      30,
-      90
-    ],
-    "type": "number"
-  }
-]New value: +[
+  {
+    "enum": [
+      "7",
+      "30",
+      "90"
+    ],
+    "type": "string"
+  },
+  {
+    "anyOf": [
+      {
+        "const": 7,
+        "type": "number"
+      },
+      {
+        "const": 30,
+        "type": "number"
+      },
+      {
+        "const": 90,
+        "type": "number"
+      }
+    ]
+  }
+]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the read-only, idempotent, closed-world profile, so the description's main contribution is the interpretive caveat that direct lift is correlated evidence rather than attributed traffic and must not be summed into referral totals — a genuinely useful disclosure that prevents analytical misuse. It also notes the rollup-only (fixed-window) nature and bounded page detail, though it says nothing about freshness or possible empty results.

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?

Two sentences, both load-bearing, with the data scope stated first and the critical non-additivity warning second. The first sentence is dense with compound modifiers ('complete-population', 'resolver-owned AI-correlated'), which costs some readability but no sentence is filler.

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?

No output schema exists, and the description does convey the data domain, windowing model, page-bound behavior, and the key semantic caveat about what the numbers mean. It leaves the returned field set and the distinction between aggregate totals and per-page classifications somewhat implicit, which is the only notable gap for a read-only analytical tool.

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

Parameters3/5

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

Schema description coverage is 100%, with both windowDays (7/30/90, default 30) and pageLimit (1–25, default 10, totals uncapped) fully documented in the schema. The description's 'fixed-window rollups' and 'bounded page details' only restate those concepts without adding syntax or edge-case behavior, so the baseline 3 applies.

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 names a specific verb and two concrete resources: complete-population GA4 Direct traffic and AI-correlated lift classifications drawn from fixed-window rollups. That distinguishes it from referral-measurement siblings, though terms like 'resolver-owned' and 'lift classifications' are internal jargon an agent may not decode without context.

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?

Usage is only implied: the closing clause about never adding lift to 'measured referral totals' hints that referral tools exist elsewhere and this one is separate, but no sibling is named and there is no explicit when-to-use or when-not-to-use statement.

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

All DevTune MCP 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