PreShiftIQ

Start an assessment

start_assessment

Read-onlyIdempotent

Returns the URL the client (the evaluating company) opens to start their operational assessment for a chosen technology category. The URL is opened by the user; this tool creates no assessment and sends nothing to a vendor. If no category is given, the tool asks the user to choose one where the assistant supports it, and otherwise returns the categories to choose from.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_assessment"
  }
}

Input Schema

Name	Required	Description	Default
`handle`	No
`vertical_id`	No

Output Schema

Name	Required	Description	Default
`url`	No
`start_url`	No
`vertical_id`	No
`conversation`	No
`display_name`	No
`choose_vertical`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 10, 2026

addedOutput schema / properties / conversation / properties / card_answers
```
Added value: +{
+  "type": "boolean"
+}
```

changedOutput schema / properties / conversation / required

Previous value: -[
-  "handle",
-  "answered",
-  "next_question"
-]New value: +[
+  "handle",
+  "answered",
+  "next_question",
+  "card_answers"
+]

Changed1 schema field changedNov 10, 2026

addedOutput schema / properties / conversation

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "answered": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "handle": {
+      "type": "string"
+    },
+    "next_question": {
+      "anyOf": [
+        {
+          "type": "null"
+        },
+        {
+          "additionalProperties": false,
+          "properties": {
+            "options": {
+              "items": {
+                "additionalProperties": false,
+                "properties": {
+                  "code": {
+                    "type": "string"
+                  },
+                  "label": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "code",
+                  "label"
+                ],
+                "type": "object"
+              },
+              "type": "array"
+            },
+            "position": {
+              "minimum": 1,
+              "type": "integer"
+            },
+            "question_id": {
+              "type": "string"
+            },
+            "text": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "single_select",
+                "multi_select"
+              ],
+              "type": "string"
+            }
+          },
+          "required": [
+            "question_id",
+            "position",
+            "text",
+            "type",
+            "options"
+          ],
+          "type": "object"
+        }
+      ]
+    }
+  },
+  "required": [
+    "handle",
+    "answered",
+    "next_question"
+  ],
+  "type": "object"
+}

Changed3 schema fields changedOct 17, 2026

changedInput schema / properties / vertical_id / enum

Previous value: -[
-  "tms",
-  "dock-scheduling",
-  "eld",
-  "carrier-vetting",
-  "fleet-management"
-]New value: +[
+  "tms",
+  "dock-scheduling",
+  "eld",
+  "carrier-vetting",
+  "fleet-management",
+  "supply-chain-procurement",
+  "yard-management"
+]

changedOutput schema / properties / choose_vertical / items / properties / vertical_id / enum

Previous value: -[
-  "tms",
-  "dock-scheduling",
-  "eld",
-  "carrier-vetting",
-  "fleet-management"
-]New value: +[
+  "tms",
+  "dock-scheduling",
+  "eld",
+  "carrier-vetting",
+  "fleet-management",
+  "supply-chain-procurement",
+  "yard-management"
+]

changedOutput schema / properties / vertical_id / enum

Previous value: -[
-  "tms",
-  "dock-scheduling",
-  "eld",
-  "carrier-vetting",
-  "fleet-management"
-]New value: +[
+  "tms",
+  "dock-scheduling",
+  "eld",
+  "carrier-vetting",
+  "fleet-management",
+  "supply-chain-procurement",
+  "yard-management"
+]

Changed3 schema fields changedOct 17, 2026

addedInput schema / properties / handle

Added value: +{
+  "maxLength": 8192,
+  "minLength": 1,
+  "pattern": "^v1\\.[A-Za-z0-9_-]{1,32}\\.[A-Za-z0-9_-]+\\.[A-Za-z0-9_-]+$",
+  "type": "string"
+}

removedOutput schema / properties / boundary_statement
```
Removed value: -{
-  "type": "string"
-}
```

removedOutput schema / required

Removed value: -[
-  "boundary_statement"
-]

Changed1 schema field changedOct 15, 2026

removedInput schema / properties / client_class

Removed value: -{
-  "default": "other",
-  "description": "Which assistant is asking: 'claude', 'chatgpt' or 'other'. Optional; 'other' when omitted. It labels the link this tool returns so PreShiftIQ can count assessments started from each assistant; it does not change the assessment.",
-  "enum": [
-    "claude",
-    "chatgpt",
-    "other"
-  ],
-  "type": "string"
-}

Changed1 schema field changedOct 6, 2026

changedInput schema / properties / client_class / description

Previous value: -"Which assistant is asking: 'claude' or 'chatgpt'. Optional; any other value is recorded as 'other'. It labels the link this tool returns so PreShiftIQ can count assessments started from each assistant; it does not change the assessment."New value: +"Which assistant is asking: 'claude', 'chatgpt' or 'other'. Optional; 'other' when omitted. It labels the link this tool returns so PreShiftIQ can count assessments started from each assistant; it does not change the assessment."

Changed1 schema field changedOct 5, 2026

addedInput schema / properties / client_class / description

Added value: +"Which assistant is asking: 'claude' or 'chatgpt'. Optional; any other value is recorded as 'other'. It labels the link this tool returns so PreShiftIQ can count assessments started from each assistant; it does not change the assessment."

First observedOct 1, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description nonetheless adds real context that the annotations cannot: the tool produces a URL that a human opens, creates no assessment, and sends nothing to a vendor. The two-branch behavior when no category is supplied is also disclosed. It stops short of describing any rate limits or what happens after the URL is opened.

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?

Three sentences, front-loaded with the primary outcome (the returned URL) and followed by the negation and the no-category branch. Each sentence earns its place. Minor cost: the parenthetical gloss 'the evaluating company' interrupts the main clause.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be described, and both the with-category and without-category paths are covered. What's missing is any account of the handle parameter and of any preconditions for the call, which leaves a meaningful hole for a tool whose schema documentation is empty. Adequate, but not complete.

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

Parameters2/5

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

Schema description coverage is 0%, so the description is the only place parameter meaning can come from — and it explains only the category concept, which maps loosely to vertical_id; the enum values themselves are left to the schema. The 'handle' parameter, an opaque pattern-constrained token that is likely a session or client identifier, is not explained anywhere. With zero schema coverage, this gap matters.

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 names a specific verb and resource: it 'returns the URL the client opens to start their operational assessment for a chosen technology category.' It also actively distinguishes itself from the mutating sibling request_assessment_submit by stating it 'creates no assessment and sends nothing to a vendor.' An agent can decide between the two without opening either schema.

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?

It clearly explains the fallback when vertical_id is omitted — ask the user to choose, or return the categories to choose from. However, it gives no explicit routing against siblings that also expose categories (for example list_verticals), and it doesn't say what precondition the caller must satisfy before calling it. The guidance is implied rather than stated.

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

All PreShiftIQ 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.