Sleepwalker

Create Sleepwalker visibility run

create_sleepwalker_visibility_run

Queue a saved AI Visibility run from prompts x platforms or explicit probes.

Use this when the user wants reportable probe results, not just prompt ideas. This starts queued work and returns quickly with a run_id; poll get_sleepwalker_visibility_run_status until the run is terminal instead of creating duplicate runs. Platforms accept canonical slugs or common labels: perplexity, openai/ChatGPT, grok, gemini. To pin AI models, pass the models map with matrix mode (per platform) or set model on explicit probes (per probe); values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Every model has its own per-probe price, defaults included; call list_sleepwalker_visibility_models for the exact credits_per_probe before quoting cost. Results record the exact model that answered each probe. The response includes credit fields when credits are reserved.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	Public page URL to analyze.
`models`	No	Per-platform model overrides for matrix mode, e.g. {"openai": "latest", "perplexity": "sonar-pro"}. Values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Platforms not listed run their default model at that model's own price; read every model's exact credits_per_probe from list_sleepwalker_visibility_models.
`probes`	No	Explicit probe list. Use when prompts, models, or locales differ per platform; otherwise use prompts x platforms, optionally with the models map.
`country`	No	Market context for analysis. Use ISO country codes such as US, NL, DE, or EE.	US
`prompts`	No	Questions to ask across selected AI platforms.
`language`	No	Language for analysis and generated text. Use ISO language codes such as en, nl, de, or et.	en
`platforms`	No	AI platforms to query. Use perplexity, openai or ChatGPT, grok or xAI, and gemini.
`competitors`	No	Optional competing brands or entities to track alongside the target.
`target_entity`	Yes	Brand, product, person, or organization to track in AI answers.
`idempotency_key`	No	Optional stable key for retries. Reusing it helps avoid duplicate queued runs.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 10, 2026

changedInput schema / $defs / McpProbeInput / properties / model / description

Previous value: -"Pin the AI model for this probe: a model id from list_sleepwalker_visibility_models, or a role keyword: latest (current flagship), prior (previous generation), default. Omit for the platform default. Each non-default model has its own per-probe credit price (varies by model, not just tier); read credits_per_probe from list_sleepwalker_visibility_models."New value: +"Pin the AI model for this probe: a model id from list_sleepwalker_visibility_models, or a role keyword: latest (current flagship), prior (previous generation), default. Omit for the platform default. Every model, including a default, resolves to its own per-probe credit price; read credits_per_probe from list_sleepwalker_visibility_models."

changedInput schema / properties / country / description

Previous value: -"Market context for analysis. Use ISO country codes such as US, NL, or DE."New value: +"Market context for analysis. Use ISO country codes such as US, NL, DE, or EE."

changedInput schema / properties / language / description

Previous value: -"Language for analysis and generated text. Use ISO language codes such as en, nl, or de."New value: +"Language for analysis and generated text. Use ISO language codes such as en, nl, de, or et."

changedInput schema / properties / models / description

Previous value: -"Per-platform model overrides for matrix mode, e.g. {\"openai\": \"latest\", \"perplexity\": \"sonar-pro\"}. Values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Platforms not listed run their default model at that model's own price (1 credit on most platforms); every model's credits_per_probe comes from list_sleepwalker_visibility_models."New value: +"Per-platform model overrides for matrix mode, e.g. {\"openai\": \"latest\", \"perplexity\": \"sonar-pro\"}. Values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Platforms not listed run their default model at that model's own price; read every model's exact credits_per_probe from list_sleepwalker_visibility_models."

Changed1 schema field changedJul 15, 2026

changedInput schema / properties / models / description

Previous value: -"Per-platform model overrides for matrix mode, e.g. {\"openai\": \"latest\", \"perplexity\": \"sonar-pro\"}. Values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Platforms not listed use their default model (1 credit per probe); each non-default model has its own per-probe price from list_sleepwalker_visibility_models."New value: +"Per-platform model overrides for matrix mode, e.g. {\"openai\": \"latest\", \"perplexity\": \"sonar-pro\"}. Values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Platforms not listed run their default model at that model's own price (1 credit on most platforms); every model's credits_per_probe comes from list_sleepwalker_visibility_models."

Changed1 schema field changedJul 15, 2026

changedInput schema / $defs / McpProbeInput / properties / model / description

Previous value: -"Pin the AI model for this probe: a model id from list_sleepwalker_visibility_models, or a role keyword: latest (current flagship), prior (previous generation), default. Omit for the platform default. Each non-default model has its own per-probe credit price (varies by model, not just tier) — read credits_per_probe from list_sleepwalker_visibility_models."New value: +"Pin the AI model for this probe: a model id from list_sleepwalker_visibility_models, or a role keyword: latest (current flagship), prior (previous generation), default. Omit for the platform default. Each non-default model has its own per-probe credit price (varies by model, not just tier); read credits_per_probe from list_sleepwalker_visibility_models."

Changed2 schema fields changedJul 13, 2026

changedInput schema / $defs / McpProbeInput / properties / model / description

Previous value: -"Pin the AI model for this probe: a model id from list_sleepwalker_visibility_models, or a role keyword: latest (current flagship), prior (previous generation), default. Omit for the platform default. Non-default models cost their tier price in credits."New value: +"Pin the AI model for this probe: a model id from list_sleepwalker_visibility_models, or a role keyword: latest (current flagship), prior (previous generation), default. Omit for the platform default. Each non-default model has its own per-probe credit price (varies by model, not just tier) — read credits_per_probe from list_sleepwalker_visibility_models."

changedInput schema / properties / models / description

Previous value: -"Per-platform model overrides for matrix mode, e.g. {\"openai\": \"latest\", \"perplexity\": \"sonar-pro\"}. Values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Platforms not listed use their default model (1 credit per probe); non-default models cost their tier price."New value: +"Per-platform model overrides for matrix mode, e.g. {\"openai\": \"latest\", \"perplexity\": \"sonar-pro\"}. Values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Platforms not listed use their default model (1 credit per probe); each non-default model has its own per-probe price from list_sleepwalker_visibility_models."

Changed4 schema fields changedJul 10, 2026

addedInput schema / $defs

Added value: +{
+  "McpProbeInput": {
+    "description": "One explicit AI Visibility probe: a prompt on a platform, optionally pinned to a model.",
+    "properties": {
+      "country": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "ISO country code; defaults to the run-level country.",
+        "title": "Country"
+      },
+      "language": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "ISO language code; defaults to the run-level language.",
+        "title": "Language"
+      },
+      "model": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Pin the AI model for this probe: a model id from list_sleepwalker_visibility_models, or a role keyword: latest (current flagship), prior (previous generation), default. Omit for the platform default. Non-default models cost their tier price in credits.",
+        "title": "Model"
+      },
+      "platform": {
+        "description": "Platform slug or label: perplexity, openai/ChatGPT, grok/xAI, gemini.",
+        "title": "Platform",
+        "type": "string"
+      },
+      "prompt": {
+        "description": "Prompt to execute on the platform.",
+        "title": "Prompt",
+        "type": "string"
+      },
+      "target_entity": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Overrides the run-level target entity for this probe.",
+        "title": "Target Entity"
+      }
+    },
+    "required": [
+      "prompt",
+      "platform"
+    ],
+    "title": "McpProbeInput",
+    "type": "object"
+  }
+}

addedInput schema / properties / models

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Per-platform model overrides for matrix mode, e.g. {\"openai\": \"latest\", \"perplexity\": \"sonar-pro\"}. Values are model ids from list_sleepwalker_visibility_models or the keywords latest / prior / default. Platforms not listed use their default model (1 credit per probe); non-default models cost their tier price.",
+  "title": "Models"
+}

changedInput schema / properties / probes / anyOf

Previous value: -[
-  {
-    "items": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "$ref": "#/$defs/McpProbeInput"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / probes / description

Previous value: -"Explicit probe objects: {prompt, platform, model?, language?, country?, target_entity?}. Set model to pin the AI model for that probe: a catalog model id, or the keywords latest / prior / default (resolved to the platform's current model for that role). Omit model for the platform default. Use probes when prompts, models, or locales differ per platform."New value: +"Explicit probe list. Use when prompts, models, or locales differ per platform; otherwise use prompts x platforms, optionally with the models map."

Changed1 schema field changedJul 10, 2026

changedInput schema / properties / probes / description

Previous value: -"Advanced explicit prompt and platform objects. Use only when prompts need per-platform control."New value: +"Explicit probe objects: {prompt, platform, model?, language?, country?, target_entity?}. Set model to pin the AI model for that probe: a catalog model id, or the keywords latest / prior / default (resolved to the platform's current model for that role). Omit model for the platform default. Use probes when prompts, models, or locales differ per platform."

Changed9 schema fields changedJun 28, 2026

addedInput schema / properties / competitors / description

Added value: +"Optional competing brands or entities to track alongside the target."

addedInput schema / properties / country / description

Added value: +"Market context for analysis. Use ISO country codes such as US, NL, or DE."

addedInput schema / properties / idempotency_key / description

Added value: +"Optional stable key for retries. Reusing it helps avoid duplicate queued runs."

addedInput schema / properties / language / description

Added value: +"Language for analysis and generated text. Use ISO language codes such as en, nl, or de."

addedInput schema / properties / platforms / description

Added value: +"AI platforms to query. Use perplexity, openai or ChatGPT, grok or xAI, and gemini."

addedInput schema / properties / probes / description

Added value: +"Advanced explicit prompt and platform objects. Use only when prompts need per-platform control."

addedInput schema / properties / prompts / description

Added value: +"Questions to ask across selected AI platforms."

addedInput schema / properties / target_entity / description

Added value: +"Brand, product, person, or organization to track in AI answers."

addedInput schema / properties / url / description
```
Added value: +"Public page URL to analyze."
```

First observedJun 28, 2026

TDQS

A4.8/5.0

Behavior4/5

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

The description discloses that the tool queues asynchronous work, returns quickly with a run_id, requires status polling, and includes credit fields when credits are reserved. This goes well beyond the annotations; it could earn a 5 but does not detail failure or terminal outcomes beyond the status-tool pointer.

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?

Six dense sentences cover the core action, mode choice, platform/model conventions, pricing caveat, result recording, and response fields without repeating the schema. The most important 'queue vs poll' guidance is front-loaded.

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?

For a 10-parameter run-creation tool with an output schema, the description covers usage intent, async lifecycle, model and pricing semantics, platform aliases, and duplicate-run avoidance. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description still adds materially by explaining matrix-mode models vs per-probe model pinning, accepted platform labels, idempotency for retries, and per-model credit pricing. It turns the schema's individual field descriptions into operational guidance.

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 description opens with a specific verb ('Queue') and object ('a saved AI Visibility run'), and immediately distinguishes the two input modes ('prompts x platforms or explicit probes'). This clearly separates it from sibling tools like create_sleepwalker_content_run and suggest_sleepwalker_visibility_prompts.

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?

It explicitly says when to use it ('when the user wants reportable probe results, not just prompt ideas') and tells the agent to poll get_sleepwalker_visibility_run_status until terminal instead of creating duplicate runs. It also points to list_sleepwalker_visibility_models for exact pricing, giving concrete alternative actions.

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

All Sleepwalker 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.

Create Sleepwalker visibility run

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources