GEO MCP by DigestSEO

Refresh AI visibility scan

refresh_brand

Trigger a new scan for a tracked brand across selected AI engines (ChatGPT, Gemini, etc.) using current prompts, returning updated visibility results.

Instructions

Run a fresh scan on selected configured engines using the brand's active prompts and return after completion. Example: brand_id='acme', engines=['chatgpt','gemini'].

Input Schema

TableJSON Schema

Name	Required	Description	Default
`engines`	No	Engines to run; omit for every configured engine.
`brand_id`	Yes	Tracked brand ID to refresh.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`message`	Yes
`run_ids`	Yes
`brand_id`	Yes
`estimated_completion_seconds`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.23Sep 23, 2026

changedInput schema / properties / brand_id / description

Previous value: -"Stable identifier of the tracked brand to refresh."New value: +"Tracked brand ID to refresh."

changedInput schema / properties / engines / description

Previous value: -"Optional engine filter. If omitted, refresh every configured engine."New value: +"Engines to run; omit for every configured engine."

Changed1 schema field changedv0.3.19Sep 22, 2026

changedInput schema / properties / engines / items / enum

Previous value: -[
-  "chatgpt",
-  "claude",
-  "perplexity",
-  "gemini",
-  "grok",
-  "ai_overviews"
-]New value: +[
+  "chatgpt",
+  "claude",
+  "perplexity",
+  "gemini",
+  "grok",
+  "ai_overviews",
+  "ai_mode"
+]

Changed1 schema field changedv0.3.18Sep 21, 2026

changedInput schema / properties / engines / items / enum

Previous value: -[
-  "chatgpt",
-  "claude",
-  "perplexity",
-  "gemini",
-  "ai_overviews"
-]New value: +[
+  "chatgpt",
+  "claude",
+  "perplexity",
+  "gemini",
+  "grok",
+  "ai_overviews"
+]

First observedv0.3.2Aug 3, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already establish readOnly=false and destructive=false. The description adds that the scan uses the brand's active prompts, runs only on selected configured engines, and returns only after completion – a useful synchronous behavior note. It stops short of explaining side effects or whether previous results are replaced.

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?

Two tight sentences plus an example; the main verb and object are front-loaded and every sentence earns its place.

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?

Given the small parameter surface, full schema descriptions, and presence of an output schema, the description covers the core behavior, input example, and completion semantics. It leaves minor gaps like runtime expectations and relationship to visibility-check siblings, but nothing essential is missing.

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?

The schema already documents both parameters at 100% coverage. The description adds a concrete example mapping brand_id and engines to values, but does not need to re-explain semantics; the schema's 'omit for every configured engine' note is the key guidance.

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 clearly identifies the action ('run a fresh scan'), the resource (brand visibility on configured engines), and the input context (active prompts). It distinguishes the tool from history/listing siblings by emphasizing 'fresh scan,' though it does not explicitly name or contrast siblings.

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?

The 'fresh scan' phrasing implies the tool is for regenerating current visibility data, and the example shows a concrete invocation. However, it never states when to prefer this over check_visibility or get_visibility_history, and gives no exclusion criteria.

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

Deploy Server