Ad Angle Map

Map ad angles

map_ad_angles

Read-onlyIdempotent

Use this when the user wants to know which persuasion angles a set of ads uses and which are missing, such as "which angles are these competitor ads missing?". Pass the ads the user already has (id, text, and optionally advertiser). Optional descriptions of images or videos are read with the text. Returns the angles ranked with counts, advertisers and example ad ids, and a list of gaps: angles no ad uses (unclaimed) or only one advertiser uses (thin), each with evidence. Identical copy from one advertiser counts once. It does not fetch ads from any ad library. Angles come from keyword matching, so gaps are leads to check, not proof that an angle works.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ads": [
        {
          "id": "1",
          "text": "50% off your first box, free delivery.",
          "advertiser": "Acme"
        },
        {
          "id": "2",
          "text": "50% off your first box, free delivery.",
          "advertiser": "Acme"
        },
        {
          "id": "3",
          "text": "Recommended by vets.",
          "advertiser": "Barkly"
        }
      ]
    },
    "name": "map_ad_angles"
  }
}

Input Schema

Name	Required	Description	Default
`ads`	Yes	Ads you already have: objects with id, text and optionally advertiser. At most 300. This tool does not fetch ads from any ad library.
`descriptions`	No	Written descriptions of the ads' images or videos, as objects with the ad id and description. They are read together with the ad text. They come from a separate offline step.

Output Schema

Name	Required	Description
`gaps`	Yes
`as_of`	Yes
`notes`	Yes
`angles`	Yes
`source`	Yes
`advertisers`	Yes
`ads_analyzed`	Yes
`unclassified`	Yes	Creatives with no recognised angle, such as text in another script or no text
`distinct_creatives`	Yes
`duplicates_collapsed`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 23, 2026

addedInput schema / examples

Added value: +[
+  {
+    "ads": [
+      {
+        "advertiser": "Acme",
+        "id": "1",
+        "text": "50% off your first box, free delivery."
+      },
+      {
+        "advertiser": "Acme",
+        "id": "2",
+        "text": "50% off your first box, free delivery."
+      },
+      {
+        "advertiser": "Barkly",
+        "id": "3",
+        "text": "Recommended by vets."
+      }
+    ]
+  }
+]

Changed1 schema field changedOct 5, 2026

removedOutput schema / properties / note_from_openkrill

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Changed1 schema field changedOct 4, 2026

addedOutput schema / properties / note_from_openkrill

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}

First observedOct 3, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already cover read-only/idempotent/closed-world, and the description adds real behavior beyond them: a dedup rule ('identical copy from one advertiser counts once'), how gaps are classified (unclaimed vs thin), and an important accuracy caveat that angles come from keyword matching so gaps are leads, not proof. That caveat would change how an agent presents results to a user.

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?

Front-loaded with the trigger sentence and the pass-the-ads precondition, then output shape, then caveats in a natural order. Every sentence carries distinct information (dedup rule, exclusion of ad-library fetching, keyword-matching caveat) with no filler.

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?

Covers input requirements, how optional descriptions combine with text, the ranking/gap output shape, dedup semantics, and the confidence caveat. With annotations and an output schema also present, an agent has everything needed to call it and to frame results correctly.

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; the description earns extra by explaining the interaction between the two params — image/video descriptions are read together with ad text and come from a separate offline step. The max-300 limit is left to the schema.

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?

States a specific verb and resource: maps persuasion angles used and missing across a supplied ad set, with a concrete user-facing example phrasing. It also scopes itself negatively ('does not fetch ads from any ad library'), but it never names the sibling validate_angle_gaps, only hinting at it via 'gaps are leads to check, not proof'.

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?

Gives an explicit triggering condition ('when the user wants to know which persuasion angles a set of ads uses and which are missing') plus a precondition that the ads must already be in hand. It states a when-not (no ad-library fetching) but does not name the alternative tool to use when the user wants gaps verified rather than surfaced.

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

All Ad Angle Map 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.