Skip to main content
Glama
Sign In

Mark

by com.use-mark.app
OverviewDiscussionsAdmin

Estimate AI Search Volume

estimate_ai_volume
Read-onlyIdempotent

Estimates how often each of 1 to 50 phrases is asked in AI assistants each month, in every active market with a location and language, without saving anything. Use it to vet a question before adding it as a buyer question. Results come back in input order, each with aiSearchVolume, the total across those markets (null when no market has an estimate), and byMarket, one row per market, highest first. The total adds up markets in different languages: read it as how widely a question is asked, not one market's demand. This is AI search volume, not the Google search volume research_keywords returns. If this refuses because the workspace is not set up, call get_setup_status and check its rows, including skipped ones. Add a phrase with save_strategy_item (kind buyer_question). Related: refresh_ai_volume, get_ai_visibility, set_up_market.

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": {
      "phrases": "<phrases>"
    },
    "name": "estimate_ai_volume"
  }
}

Input Schema

NameRequiredDescriptionDefault
phrasesYesOne to 50 phrases, each up to 250 characters.

Output Schema

NameRequiredDescriptionDefault
scopeYesWhat the run checks.
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • removedOutput schema / properties / market
      Removed value: -{
-  "additionalProperties": false,
-  "properties": {
-    "id": {
-      "type": "string"
-    },
-    "name": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "id",
-    "name"
-  ],
-  "type": "object"
-}
    • changedOutput schema / properties / results / items / properties / aiSearchVolume / description
      Previous value: -"Monthly estimate; null when there is none."New value: +"Monthly estimate summed across markets; null when no market has one."
    • addedOutput schema / properties / results / items / properties / byMarket
      Added value: +{
+  "description": "Every market, highest first, markets with none last.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "aiSearchVolume": {
+        "description": "Monthly estimate; null when there is none.",
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "country": {
+        "type": "string"
+      },
+      "market": {
+        "type": "string"
+      },
+      "marketId": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "marketId",
+      "market",
+      "country",
+      "aiSearchVolume"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • changedOutput schema / properties / results / items / required
      Previous value: -[
-  "phrase",
-  "aiSearchVolume"
-]New value: +[
+  "phrase",
+  "aiSearchVolume",
+  "byMarket"
+]
    • changedOutput schema / required
      Previous value: -[
-  "market",
-  "results",
-  "scope"
-]New value: +[
+  "results",
+  "scope"
+]
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description is free to add behavior the annotations cannot: nothing is persisted, results return in input order, aiSearchVolume is null when no market has an estimate, byMarket is sorted highest first, and the cross-language total must not be read as single-market demand. It also discloses the refusal condition (workspace not set up), which is genuinely actionable beyond the hints.

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?

Front-loaded with the core verb, resource, scope, and the no-save guarantee, then return shape, then interpretation caveat, then recovery and related tools — a sensible priority order with no filler. The opening sentence is long and carries several clauses at once, and the related-tools tail is slightly list-like, but every sentence adds usable information.

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?

Complete for a single-parameter read tool: it covers scope, non-persistence, return structure and null semantics, the interpretive trap of a cross-language total, failure recovery, and next-step tools. With an output schema present it did not need to describe return fields, yet doing so here clarifies interpretation rather than duplicating types.

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% and the single parameter is fully documented, so the baseline is 3; the description earns above that by framing what a 'phrase' means here (an AI-assistant question, candidate buyer question) and tying result ordering to input order. It does not add syntax or formatting detail beyond the schema's length and count constraints, which it largely restates.

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?

States a specific verb and resource — estimating monthly AI-assistant ask frequency for 1-50 phrases across active markets — and explicitly distinguishes itself from research_keywords (Google volume) and refresh_ai_volume. An agent can identify it among ~90 siblings without opening the schema.

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

Usage Guidelines5/5

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

Gives an explicit use case (vet a question before adding it as a buyer question), a named alternative for the different metric (research_keywords), the follow-up mutation path (save_strategy_item with kind buyer_question), and a recovery path when the call refuses (get_setup_status, including skipped rows). Conditions that select each tool are stated rather than implied.

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

All Mark 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