Skip to main content
Glama
Sign In

Cite42: AI visibility and SEO data for AI agents

by dev.cite42
OverviewDiscussionsAdmin

cite42_tracker_update

Destructive

Replace a tracker definition: name, cadence, measurement, prompts and configuration. Send the complete definition, not a partial patch — a tracker read returns this exact shape, so read it, change what you need, and send it back. Editing returns the tracker to draft so the new recurring cost can be confirmed. Managing trackers and reading reports is free; each run bills one call per prompt at the per-surface rates, or one check per keyword for keyword_rankings.

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": {
      "trackerId": "<trackerId>",
      "name": "<name>",
      "cadence": "<cadence>",
      "primitive": "<primitive>"
    },
    "name": "cite42_tracker_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoCitations only: a URL to report on as cited or not cited.
nameYesHuman-readable tracker name, for example "Weekly AI visibility".
brandNoRequired for compare and sentiment. Not used by rankings or citations.
deviceNokeyword_rankings only: desktop or mobile results. Defaults to desktop.
domainNokeyword_rankings only: the site to find in Google results, e.g. example.com.
modelsNoAI surfaces to query for every prompt. Omit for the three defaults (chatgpt = the OpenAI API, perplexity, gemini), or list surfaces explicitly to set the recurring cost; chatgpt_app (ChatGPT itself, captured from its web interface) is opt-in. There is no fullSweep here: a saved tracker stores the exact list it was authorized for.
cadenceYes
countryNoISO-2 country. keyword_rankings: the Google market, defaults to "us". AI measurements: optional country to measure from; omit for each surface's default. On an update of an AI tracker, omitting it keeps the stored market and null removes it.
promptsNoAI measurements: the prompts to run on every scheduled run, up to 30. Each one is billed as its own call. Not used by keyword_rankings.
keywordsNokeyword_rankings only: up to 100 keywords, each with an optional target page. Each keyword is billed as its own check on every run.
languageNoISO-2 language, defaulting to the country's main language. AI measurements use it only for google_ai_overview and chatgpt_app, and need a country with it.
primitiveYesWhat to measure: rankings, compare, citations or sentiment run across AI surfaces for every prompt; keyword_rankings checks Google positions of a domain for every keyword. One measurement per tracker.
trackerIdYesCite42 tracker ID returned by a tracker management or report tool.
competitorsNoRequired for rankings (the brands to track, including your own) and compare (the rivals to rank against, up to 10). Not used by citations or sentiment.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / models / description
      Previous value: -"AI surfaces to query for every prompt. Omit for the three defaults (chatgpt, perplexity, gemini), or list surfaces explicitly to set the recurring cost; chatgpt_app (the ChatGPT app itself) is opt-in. There is no fullSweep here: a saved tracker stores the exact list it was authorized for."New value: +"AI surfaces to query for every prompt. Omit for the three defaults (chatgpt = the OpenAI API, perplexity, gemini), or list surfaces explicitly to set the recurring cost; chatgpt_app (ChatGPT itself, captured from its web interface) is opt-in. There is no fullSweep here: a saved tracker stores the exact list it was authorized for."
  2. Changed16 schema fields changed
    • addedInput schema / properties / country
      Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 8,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "ISO-2 country. keyword_rankings: the Google market, defaults to \"us\". AI measurements: optional country to measure from; omit for each surface's default. On an update of an AI tracker, omitting it keeps the stored market and null removes it."
+}
    • addedInput schema / properties / device
      Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "desktop",
+        "mobile"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "keyword_rankings only: desktop or mobile results. Defaults to desktop."
+}
    • addedInput schema / properties / domain
      Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 200,
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "keyword_rankings only: the site to find in Google results, e.g. example.com."
+}
    • addedInput schema / properties / keywords
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "properties": {
+          "keyword": {
+            "description": "A search term as people type it into Google.",
+            "maxLength": 200,
+            "minLength": 1,
+            "type": "string"
+          },
+          "page": {
+            "anyOf": [
+              {
+                "maxLength": 500,
+                "minLength": 1,
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Optional page on the site that should rank for it: a full URL or a path such as /pricing."
+          }
+        },
+        "required": [
+          "keyword"
+        ],
+        "type": "object"
+      },
+      "maxItems": 100,
+      "minItems": 1,
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "keyword_rankings only: up to 100 keywords, each with an optional target page. Each keyword is billed as its own check on every run."
+}
    • addedInput schema / properties / language
      Added value: +{
+  "anyOf": [
+    {
+      "maxLength": 8,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "ISO-2 language, defaulting to the country's main language. AI measurements use it only for google_ai_overview and chatgpt_app, and need a country with it."
+}
    • changedInput schema / properties / models / anyOf
      Previous value: -[
-  {
-    "items": {
-      "enum": [
-        "chatgpt",
-        "claude",
-        "perplexity",
-        "gemini",
-        "google_ai_overview"
-      ],
-      "type": "string"
-    },
-    "minItems": 1,
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "enum": [
+        "chatgpt",
+        "claude",
+        "perplexity",
+        "gemini",
+        "google_ai_overview",
+        "chatgpt_app"
+      ],
+      "type": "string"
+    },
+    "minItems": 1,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / models / description
      Previous value: -"AI surfaces to query for every prompt. Omit for the three defaults (chatgpt, perplexity, gemini), or list surfaces explicitly — including all five — to set the recurring cost. There is no fullSweep here: a saved tracker stores the exact list it was authorized for."New value: +"AI surfaces to query for every prompt. Omit for the three defaults (chatgpt, perplexity, gemini), or list surfaces explicitly to set the recurring cost; chatgpt_app (the ChatGPT app itself) is opt-in. There is no fullSweep here: a saved tracker stores the exact list it was authorized for."
    • changedInput schema / properties / primitive / description
      Previous value: -"What to measure on every prompt: rankings (which brands get named), compare (your brand against named competitors), citations (which sources the models' web search surfaces), or sentiment (how one brand is described). One measurement per tracker — use a second tracker for a second one."New value: +"What to measure: rankings, compare, citations or sentiment run across AI surfaces for every prompt; keyword_rankings checks Google positions of a domain for every keyword. One measurement per tracker."
    • changedInput schema / properties / primitive / enum
      Previous value: -[
-  "rankings",
-  "compare",
-  "citations",
-  "sentiment"
-]New value: +[
+  "rankings",
+  "compare",
+  "citations",
+  "sentiment",
+  "keyword_rankings"
+]
    • addedInput schema / properties / prompts / anyOf
      Added value: +[
+  {
+    "items": {
+      "maxLength": 2000,
+      "minLength": 1,
+      "type": "string"
+    },
+    "maxItems": 30,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]
    • changedInput schema / properties / prompts / description
      Previous value: -"The prompts to run on every scheduled run, up to 30. Each one is billed as its own call. Keep the wording stable so runs stay comparable, avoid dates, and do not repeat a prompt."New value: +"AI measurements: the prompts to run on every scheduled run, up to 30. Each one is billed as its own call. Not used by keyword_rankings."
    • removedInput schema / properties / prompts / items
      Removed value: -{
-  "maxLength": 2000,
-  "minLength": 1,
-  "type": "string"
-}
    • removedInput schema / properties / prompts / maxItems
      Removed value: -30
    • removedInput schema / properties / prompts / minItems
      Removed value: -1
    • removedInput schema / properties / prompts / type
      Removed value: -"array"
    • changedInput schema / required
      Previous value: -[
-  "trackerId",
-  "name",
-  "cadence",
-  "primitive",
-  "prompts"
-]New value: +[
+  "trackerId",
+  "name",
+  "cadence",
+  "primitive"
+]
  3. Changed1 schema field changed
    • changedInput schema / required
      Previous value: -[
-  "trackerId",
-  "cadence",
-  "primitive",
-  "prompts"
-]New value: +[
+  "trackerId",
+  "name",
+  "cadence",
+  "primitive",
+  "prompts"
+]
  4. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the destructiveHint=true annotation, it discloses two side effects an agent couldn't otherwise know: editing pushes the tracker back to draft so the new recurring cost must be confirmed, and it explains the billing model (one call per prompt per run at per-surface rates, or one check per keyword for keyword_rankings). That is exactly the extra context annotations cannot carry.

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?

Three sentences, front-loaded with the replace semantics, then the read-modify-write rule, then cost/state side effects. Very little waste; the pricing sentence is broad but relevant because it explains why the draft-confirmation step matters. It could be tightened slightly but nothing 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?

For a 14-parameter destructive replacement with no output schema, the description covers the critical unknowns: full-shape send, draft-state side effect, and billing consequences. Remaining gaps are minor (what happens to an in-flight run, whether the tracker ID is preserved), so an agent can still call it 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 93%, so the per-field documentation is already in the schema and the baseline is 3. The description still adds real meaning by clarifying that the whole definition must be sent because a tracker read returns this exact shape — this tells the agent that omitting optional fields is not a preserve-existing semantics, which is not stated per-parameter in 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?

The description opens with a specific verb and resource ("Replace a tracker definition") and enumerates the fields covered (name, cadence, measurement, prompts, configuration). It implicitly separates itself from a partial-update sibling by insisting on a full replacement, but it never names create/activate/pause/etc., so an agent must infer the boundary against those siblings.

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 concrete workflow: read the tracker, change what you need, send the exact shape back, rather than sending a patch. What's missing is explicit routing against the other tracker siblings — nothing says to use tracker_create for new trackers or tracker_activate to resume, so the agent has to reason that this tool only mutates existing definitions.

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

All Cite42: AI visibility and SEO data for AI agents 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