Convika

Set AI answer check questions

update_answer_check_prompts

Idempotent

Use this tool when the user wants to set up checking whether ChatGPT, Perplexity, Gemini, or Google AI Overviews mention their brand or link to their site (ホームページ, Webサイト, ランディングページ): 「ChatGPT でうちの名前が出るか調べたい」「AI の回答に載っているか確かめたい」, "track whether AI answers recommend us".

Saves the workspace's AI answer check: its questions, the brand names to look for in the answers, and its domains outside Convika (外部サイト) to look for in the cited links. Saving asks nothing: run_answer_check asks the saved questions when the user wants. Questions kept per plan: Free: 10, Pro: 50, MAX: 200. Each question up to 200 characters, about the user's own brand or market (what their customers would ask an AI), with no URLs; harmful questions are refused. Up to 3 brand names (other spellings, such as the Japanese name) and 3 domains: the workspace's external sites (外部サイト), such as a store on another service. Every site the workspace's pages are served on (their convika.page and older convika.com URLs, and its custom domains) counts as its own without being saved. convika.page, convika.com, and their URLs are refused (shared_domain), since every Convika page uses them.

prompts adds questions and changes saved ones: a question with a saved one's text changes that one (its target page), and any other text is a new question at the end. Questions left out stay as they are, with their results, so prompts holds only the questions to add or change. Convika reads the whole saved list first and merges.
This tool deletes nothing. remove_answer_check_prompts deletes saved questions, with their results. A question's wording changes by removing the old text there and adding the new one here, which starts with no results.
brands and domains, when given, replace the saved ones; leave them out to keep them.
Target pages: each question can point at the page meant to answer it. Give {text, targetPath} with the page's path, such as "/guides/how-to-choose" (its full URL when different pages use that path on two of the workspace's sites), or {text, targetPageId} with its siteId. Convika finds a path among get_brand's pages. {text, targetPageId: null} clears a question's target page. A question given as text alone keeps the page it already has, and a new one that matches a saved suggestion takes the page it was suggested from.
A targetPath with no page yet saves its question with no target page and comes back in unresolvedTargets. Once a page is at that path (create_pages, or create_page for one), sending that question again with its targetPath links it. A targetPath that names no single page of the workspace saves nothing (invalid_target).
A run needs at least one brand name.
host: to work on one site of a workspace with several, name it as get_brand's sites list it. Convika then reads and merges that site's questions alone, a path in targetPath is a page of that site, and a page on another site is refused (unknown_page). The brand names given apply to that site, and the other sites keep theirs. A site this workspace doesn't have saves nothing (unknown_site). Left out, the call works on the whole workspace.
expectedBrandId: with get_brand's id, a connection that now works on another workspace changes nothing (brand_mismatch). Returns changes (added, updated, removed, kept) and the saved state, as get_answer_check_results does with no filter: the first questions that fit in about 6,000 tokens.

Input Schema

Name	Required	Description
`host`	No	One of the workspace's sites, as get_brand's sites list it, such as 'www.sakura-cafe.com': the call works on that site's questions and brand names alone. Left out: the whole workspace.
`brands`	No	Brand names to look for in the answers, such as ['Sakura Cafe', 'さくらカフェ']
`remove`	No	No longer used: deleting questions moved to remove_answer_check_prompts. A call with remove saves nothing.
`domains`	No	The workspace's external sites (外部サイト), such as ['shop.sakura-cafe.com']; subdomains count too. Its Convika sites count without being listed.
`prompts`	No	Only the questions to add or change: text such as 'best landing page builder for a café', or {text, targetPath} to point a question at its page. Saved questions left out stay.
`expectedBrandId`	No	The workspace's id from get_brand. When the connection now works on another workspace (the dashboard's active workspace was switched), the call changes nothing and answers brand_mismatch.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

addedInput schema / properties / host

Added value: +{
+  "description": "One of the workspace's sites, as get_brand's sites list it, such as 'www.sakura-cafe.com': the call works on that site's questions and brand names alone. Left out: the whole workspace.",
+  "maxLength": 253,
+  "minLength": 1,
+  "type": "string"
+}

Changed3 schema fields changedNov 2, 2026

changedInput schema / properties / domains / description

Previous value: -"The brand's addresses outside Convika (外部サイト), such as ['shop.sakura-cafe.com']; subdomains count too. Its Convika hosts count without being listed."New value: +"The workspace's external sites (外部サイト), such as ['shop.sakura-cafe.com']; subdomains count too. Its Convika sites count without being listed."

changedInput schema / properties / expectedBrandId / description

Previous value: -"The brand's id from get_brand. When the connection now works on another brand (the dashboard's active workspace was switched), the call changes nothing and answers brand_mismatch."New value: +"The workspace's id from get_brand. When the connection now works on another workspace (the dashboard's active workspace was switched), the call changes nothing and answers brand_mismatch."

changedInput schema / properties / prompts / items / anyOf

Previous value: -[
-  {
-    "maxLength": 200,
-    "type": "string"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "targetPageId": {
-        "anyOf": [
-          {
-            "maxLength": 100,
-            "minLength": 1,
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "description": "That page's siteId instead of its path; null clears the target page"
-      },
-      "targetPath": {
-        "description": "The path of the brand's page meant to answer it, such as '/guides/how-to-choose', or that page's full URL",
-        "maxLength": 300,
-        "type": "string"
-      },
-      "text": {
-        "description": "The question",
-        "maxLength": 200,
-        "type": "string"
-      }
-    },
-    "required": [
-      "text"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "maxLength": 200,
+    "type": "string"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "targetPageId": {
+        "anyOf": [
+          {
+            "maxLength": 100,
+            "minLength": 1,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "That page's siteId instead of its path; null clears the target page"
+      },
+      "targetPath": {
+        "description": "The path of the workspace's page meant to answer it, such as '/guides/how-to-choose', or that page's full URL",
+        "maxLength": 300,
+        "type": "string"
+      },
+      "text": {
+        "description": "The question",
+        "maxLength": 200,
+        "type": "string"
+      }
+    },
+    "required": [
+      "text"
+    ],
+    "type": "object"
+  }
+]

Changed4 schema fields changedNov 1, 2026

changedInput schema / properties / remove / description

Previous value: -"Saved questions to delete, by id or by text; their results go with them"New value: +"No longer used: deleting questions moved to remove_answer_check_prompts. A call with remove saves nothing."

removedInput schema / properties / remove / items / minLength
```
Removed value: -1
```
removedInput schema / properties / remove / maxItems
```
Removed value: -200
```
removedInput schema / properties / remove / minItems
```
Removed value: -1
```

Changed7 schema fields changedNov 1, 2026

changedInput schema / properties / domains / description

Previous value: -"The workspace's own domains, such as ['sakura-cafe.com']; subdomains count too"New value: +"The brand's addresses outside Convika (外部サイト), such as ['shop.sakura-cafe.com']; subdomains count too. Its Convika hosts count without being listed."

addedInput schema / properties / expectedBrandId

Added value: +{
+  "description": "The brand's id from get_brand. When the connection now works on another brand (the dashboard's active workspace was switched), the call changes nothing and answers brand_mismatch.",
+  "maxLength": 100,
+  "minLength": 1,
+  "type": "string"
+}

changedInput schema / properties / prompts / description

Previous value: -"The whole list of questions, in order, such as 'best landing page builder for a café'"New value: +"Only the questions to add or change: text such as 'best landing page builder for a café', or {text, targetPath} to point a question at its page. Saved questions left out stay."

addedInput schema / properties / prompts / items / anyOf

Added value: +[
+  {
+    "maxLength": 200,
+    "type": "string"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "targetPageId": {
+        "anyOf": [
+          {
+            "maxLength": 100,
+            "minLength": 1,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "That page's siteId instead of its path; null clears the target page"
+      },
+      "targetPath": {
+        "description": "The path of the brand's page meant to answer it, such as '/guides/how-to-choose', or that page's full URL",
+        "maxLength": 300,
+        "type": "string"
+      },
+      "text": {
+        "description": "The question",
+        "maxLength": 200,
+        "type": "string"
+      }
+    },
+    "required": [
+      "text"
+    ],
+    "type": "object"
+  }
+]

removedInput schema / properties / prompts / items / maxLength
```
Removed value: -200
```
removedInput schema / properties / prompts / items / type
```
Removed value: -"string"
```

addedInput schema / properties / remove

Added value: +{
+  "description": "Saved questions to delete, by id or by text; their results go with them",
+  "items": {
+    "maxLength": 200,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 200,
+  "minItems": 1,
+  "type": "array"
+}

Changed1 schema field changedOct 30, 2026
- changedInput schema / properties / prompts / maxItems
```
Previous value: -50New value: +200
```
AddedOct 28, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the annotations, the description discloses important behavior: prompts are merged rather than replacing the saved list, brands and domains replace when provided, plan limits and character limits apply, harmful questions are refused, Convika domains are refused as shared_domain, and target-path errors surface as unresolvedTargets or invalid_target. It also explains host scope, expectedBrandId mismatch behavior, and what the return payload contains.

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?

The description is front-loaded with the user intent and then organizes details into useful bullets, but it is quite long and dense for a tool description. The length is largely justified by the complexity of merge, target-page, host, and error semantics, though the lack of headings or tighter grouping makes it slightly harder to scan than an ideal 5 would be.

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 complex mutation tool with no output schema, the description is complete enough to invoke correctly: it covers merge behavior, deletion boundaries, limits, refusals, target-page resolution, host scoping, expectedBrandId, and the returned changes and saved state. An agent has the context needed to avoid the main failure modes.

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?

Although schema coverage is already 100%, the description adds substantial meaning beyond the schema: it explains how prompts merge with existing questions, how targetPath and targetPageId resolve or clear targets, when unresolvedTargets occurs, how host scopes the operation to one site, and why expectedBrandId prevents cross-workspace changes. These are behavioral parameter semantics that the schema alone does not fully convey.

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-and-resource purpose: setting up AI answer checks for whether ChatGPT, Perplexity, Gemini, or Google AI Overviews mention the user's brand or link to their site. It also names the related siblings run_answer_check, remove_answer_check_prompts, and get_answer_check_results, so an agent can distinguish this tool from its alternatives.

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 this tool versus related tools: saving asks nothing and run_answer_check asks the saved questions later, while this tool deletes nothing and remove_answer_check_prompts handles deletion. It also gives concrete user-intent examples in both English and Japanese, leaving little ambiguity about selection.

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

All Convika 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.

Set AI answer check questions

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources