Sync by CHNLSYNC

Ask the Sync advisor

ask_sync_advisor

Consult CHNLSYNC's advisor about the user's IT environment.

First call: omit session_id/session_token and provide company_name plus pain (a plain-language description of what is not working) — a private advisor workspace is created and its credentials are returned. Later calls: pass session_id, session_token AND conversation_id back to continue the same conversation. Persist all three privately across turns. Incomplete continuation handles are rejected before any write; recover the previous tool result instead of creating another workspace. Never automatically retry a failed write: it may already have been recorded. Replies never contain supplier names or pricing — those come only after a human broker review, via the claim_url or a requested callback.

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": {
      "message": "<message>"
    },
    "name": "ask_sync_advisor"
  }
}

Input Schema

Name	Required	Description
`pain`	No	What is not working; required for a new workspace.
`message`	Yes	The user's technology question; no secrets.
`session_id`	No	Returned workspace ID; required for continuation.
`company_name`	No	Company name; required for a new workspace.
`session_token`	No	Returned private token; required with session_id.
`conversation_id`	No	Returned conversation ID; required for follow-up turns.

Output Schema

Name	Required	Description
`claim_url`	Yes	Private claim link; share only with the workspace owner.
`disclosure`	Yes	Human review precedes supplier and pricing disclosure.
`session_id`	Yes	Workspace handle to retain with conversation_id.
`missing_info`	No	Initial information gaps.
`review_status`	Yes	Current human-review status, when available.
`session_token`	Yes	Private credential; retain, never publish.
`conversation_id`	Yes	Pass back with both session credentials next turn.
`assistant_message`	Yes	Buyer-safe advisor response.
`environment_summary`	No	Initial workspace summary.
`follow_up_questions`	Yes	Questions that clarify the user's needs.

Schema Changelog

Changes observed during successful MCP inspections.

Changed18 schema fields changedSep 9, 2026

changedInput schema / properties / company_name / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maxLength": 255,
+    "minLength": 1,
+    "pattern": "\\S",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / company_name / description

Added value: +"Company name; required for a new workspace."

addedInput schema / properties / conversation_id

Added value: +{
+  "anyOf": [
+    {
+      "pattern": "^[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12}$",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Returned conversation ID; required for follow-up turns."
+}

addedInput schema / properties / message / description

Added value: +"The user's technology question; no secrets."

addedInput schema / properties / message / maxLength
```
Added value: +8000
```
addedInput schema / properties / message / minLength
```
Added value: +1
```
addedInput schema / properties / message / pattern
```
Added value: +"\\S"
```

changedInput schema / properties / pain / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maxLength": 4000,
+    "minLength": 1,
+    "pattern": "\\S",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / pain / description

Added value: +"What is not working; required for a new workspace."

changedInput schema / properties / session_id / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "pattern": "^[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12}$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / session_id / description

Added value: +"Returned workspace ID; required for continuation."

changedInput schema / properties / session_token / anyOf

Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maxLength": 512,
+    "minLength": 1,
+    "pattern": "^\\S+$",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / session_token / description

Added value: +"Returned private token; required with session_id."

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / description

Added value: +"An advisor reply with the complete handle needed to continue safely."

addedOutput schema / properties

Added value: +{
+  "assistant_message": {
+    "description": "Buyer-safe advisor response.",
+    "title": "Assistant Message",
+    "type": "string"
+  },
+  "claim_url": {
+    "description": "Private claim link; share only with the workspace owner.",
+    "title": "Claim Url",
+    "type": "string"
+  },
+  "conversation_id": {
+    "description": "Pass back with both session credentials next turn.",
+    "format": "uuid",
+    "title": "Conversation Id",
+    "type": "string"
+  },
+  "disclosure": {
+    "description": "Human review precedes supplier and pricing disclosure.",
+    "title": "Disclosure",
+    "type": "string"
+  },
+  "environment_summary": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Initial workspace summary.",
+    "title": "Environment Summary"
+  },
+  "follow_up_questions": {
+    "description": "Questions that clarify the user's needs.",
+    "items": {
+      "type": "string"
+    },
+    "title": "Follow Up Questions",
+    "type": "array"
+  },
+  "missing_info": {
+    "anyOf": [
+      {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Initial information gaps.",
+    "title": "Missing Info"
+  },
+  "review_status": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "description": "Current human-review status, when available.",
+    "title": "Review Status"
+  },
+  "session_id": {
+    "description": "Workspace handle to retain with conversation_id.",
+    "format": "uuid",
+    "title": "Session Id",
+    "type": "string"
+  },
+  "session_token": {
+    "description": "Private credential; retain, never publish.",
+    "minLength": 1,
+    "title": "Session Token",
+    "type": "string"
+  }
+}

addedOutput schema / required

Added value: +[
+  "assistant_message",
+  "follow_up_questions",
+  "conversation_id",
+  "review_status",
+  "claim_url",
+  "disclosure",
+  "session_id",
+  "session_token"
+]

addedOutput schema / title
```
Added value: +"AdvisorResponse"
```

First observedSep 6, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already flag a non-read-only, non-idempotent, non-destructive write, and the description adds genuinely new behavioral context: a workspace is created and its credentials returned, incomplete continuation handles are rejected before any write, and failed writes must not be retried because they may already have been recorded. The only real gap is that it does not describe the shape or latency of advisor replies, but the output schema exists to cover that.

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 purpose is front-loaded in sentence one and every subsequent sentence carries operational weight (first call, continuation, retry, disclosure limits). It is dense rather than padded, though the credential-persistence and rejection sentences could be tightened slightly.

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 stateful, credential-bearing multi-turn tool with annotations and an output schema, the description covers the full lifecycle: workspace creation, handle persistence, continuation, failure handling, and the limits of what replies contain. Nothing an agent needs in order to call it correctly across turns appears to be missing.

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 description coverage is 100%, so the baseline is 3, but the description adds conditional semantics the schema cannot express: which parameter combination is required per call phase and the instruction to persist all three handles privately across turns. It stops short of explaining the UUID/token formats, which the schema patterns already handle.

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 gives a specific verb and resource (consult CHNLSYNC's advisor about the user's IT environment), and the closing paragraph draws the boundary with the sibling broker flow by stating that supplier names and pricing only arrive after human broker review via claim_url or a requested callback. An agent can tell what this tool is and where it stops without opening the schema.

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 separates the first call (omit session_id/session_token, supply company_name plus pain) from continuation calls (session_id, session_token AND conversation_id), and adds recovery guidance (reuse the previous tool result rather than creating another workspace) plus a no-auto-retry rule. Nothing about when to use it or how to sequence turns is left to inference.

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

All Sync by CHNLSYNC 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?