Mark

Run AI Answer Check

run_answer_engine_check

Starts this week's AI answer check now, the same weekly run the schedule would start, and reports where it stands. There is at most one run per week, so calling it again returns that run with its progress (completed, failed and expected counts) and does not start a second. A workspace exempt from the weekly limit gets a new run instead once this week's run has finished; the earlier run and its answers are kept, and AI answers keeps showing them until the new run finishes. Also says when the next run is due, or why nothing was started: AI answer checks are off (an admin turns them on in Settings > Workspace; this tool does not), no buyer questions, or no market location. Covers every active market with a location; it takes no market. One run asks every active question in every such market on 6 engines (ChatGPT, Gemini, AI Overview, AI Mode, Claude and Perplexity; Claude and Perplexity through their APIs with web search on, not the consumer apps); scope.summary states it as questions × engines = checks (× markets when more than one), and get_ai_visibility's nextAnswerCheck shows it before you start. When this week's run exists, scope is that run's. Limited to 10 calls a minute per workspace when rate limiting is configured; otherwise calls pass, and the one-run-a-week rule still holds for every other workspace. Related: get_ai_visibility, set_up_market.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description
`run`	No
`scope`	Yes	What the run checks.
`state`	Yes
`appUrl`	Yes
`nextRunOn`	No	The Monday the next weekly run is due, YYYY-MM-DD (UTC).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 14, 2026

addedOutput schema / properties / scope

Added value: +{
+  "additionalProperties": false,
+  "description": "What the run checks.",
+  "properties": {
+    "summary": {
+      "description": "The same line the app shows beside the button.",
+      "type": "string"
+    },
+    "units": {
+      "description": "How many checks, pages or questions.",
+      "type": "number"
+    }
+  },
+  "required": [
+    "units",
+    "summary"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "state",
-  "appUrl"
-]New value: +[
+  "state",
+  "scope",
+  "appUrl"
+]

AddedOct 8, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Without relying on annotations, it discloses that calling again reuses the existing run, what happens for exempt workspaces (new run only after the prior finishes, old run and answers retained), the exposed rate limit (10 calls/min per workspace), and the engine set used. Annotations only say non-readOnly, openWorld, non-idempotent; the description adds substantial operational context on top.

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?

Purpose is front-loaded in the first sentence and each subsequent sentence carries distinct information (idempotent-ish reuse, exemptions, rate limit, scope). It is dense and long, with some nested asides that could be tightened, but little is pure 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?

An output schema exists, yet the description still summarizes what comes back (progress, completed/failed/expected counts, next run timing, reasons for no start). Combined with the annotations and the scope.summary explanation, an agent has everything needed to call this 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?

There are zero parameters, so the baseline is 4. The description usefully notes 'it takes no market' and explains that scope covers all active markets, which clarifies the absence of a targeting parameter.

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 first sentence states a specific verb and resource ('Starts this week's AI answer check now') and immediately scopes it as the same run a schedule would kick off. It distinguishes itself from get_ai_visibility by framing that tool's nextAnswerCheck as a pre-check rather than the trigger.

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 concrete conditions under which nothing starts (checks off, no buyer questions, no market location) and points to related tools (get_ai_visibility, set_up_market). It does not explicitly state 'use get_ai_visibility instead if you only want status', so the alternative routing is implied rather than named.

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

All Mark 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.

Resources

Need Help?