swsd-mcp

swsd_create_service_request

Submit a SolarWinds Service Desk catalog request by creating a service-request incident with a specified catalog item and form variable values; returns the incident ID for follow-up.

Instructions

Submit a SWSD catalog request, creating an incident with is_service_request: true (auto-set by SWSD on this endpoint) and the supplied form variable values. Use swsd_list_catalog_items to find the right catalog_item_id and swsd_get_catalog_item to inspect its variables before filling. Each request_variables entry needs custom_field_id (= the catalog item variable's id) and value (stringified to match the variable's kind — for dropdowns, one of the options choices). The created incident's id is returned for follow-up calls (swsd_get_incident, swsd_assign_incident, etc.). WRITE — does not retry on transient failure; the agent should verify with swsd_get_incident before retrying. To set tenant-specific custom field values, pass custom_fields: [{name, value}] — call swsd_describe_custom_fields first to discover field names and (for Dropdowns) allowed values. Validated for Text, Dropdown, Number, Checkbox, and Date types.

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": {
      "catalog_item_id": "<catalog_item_id>"
    },
    "name": "swsd_create_service_request"
  }
}

Input Schema

Name	Required	Description
`description`	No	Optional free-text description added to the resulting incident. The catalog item's default description from the SWSD UI is replaced if you pass this.
`custom_fields`	No	Set tenant-specific custom field values on the record. Multi_picklist and User-type fields are not yet supported by this tool (set those via the SWSD UI). Validated for Text, Dropdown, Number, Checkbox, and Date types.
`catalog_item_id`	Yes	Catalog item id from `swsd_list_catalog_items` or `swsd_get_catalog_item`. The endpoint URL embeds this; SWSD auto-populates the resulting incident's name, category, and subcategory from the catalog item.
`requester_email`	No	Email of the user the request is for. Defaults to the authenticated user (resolved from the JWT). SWSD rejects numeric requester ids on this endpoint, so pass an email if you need to file the request on behalf of someone else.
`request_variables`	No	Form variable values, one entry per catalog variable being filled. Use `swsd_get_catalog_item` first to discover the available variables and required ones (`required: "1"`).

Output Schema

Name	Required	Description	Default
`dry_run`	No
`request`	No
`incident`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv3.3.0Nov 5, 2026

addedOutput schema / properties / dry_run

Added value: +{
+  "const": true,
+  "type": "boolean"
+}

addedOutput schema / properties / request

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "body": {},
+    "method": {
+      "type": "string"
+    },
+    "path": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "method",
+    "path"
+  ],
+  "type": "object"
+}

removedOutput schema / required
```
Removed value: -[
-  "incident"
-]
```

Changed3 schema fields changedv3.0.0Oct 4, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedInput schema / properties / requester_email / pattern

Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Changed7 schema fields changedv2.3.1Aug 22, 2026
- addedInput schema / properties / custom_fields / items / properties / name / maxLength
```
Added value: +500
```
- changedInput schema / properties / custom_fields / items / properties / value / anyOf
```
Previous value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  },
-  {
-    "type": "boolean"
-  }
-]New value: +[
+  {
+    "maxLength": 100000,
+    "type": "string"
+  },
+  {
+    "type": "number"
+  },
+  {
+    "type": "boolean"
+  }
+]
```
- addedInput schema / properties / custom_fields / maxItems
```
Added value: +100
```
- addedInput schema / properties / description / maxLength
```
Added value: +100000
```
- addedInput schema / properties / request_variables / items / properties / value / maxLength
```
Added value: +100000
```
- addedInput schema / properties / request_variables / maxItems
```
Added value: +100
```
- addedInput schema / properties / requester_email / maxLength
```
Added value: +320
```
First observedv2.1.0May 28, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already flag this as a non-idempotent write in an open world, and the description adds real behavior on top: the endpoint auto-sets `is_service_request`, it does not retry on transient failures, requester defaults to the JWT user, numeric requester ids are rejected, and Multi_picklist/User field types are unsupported. These are non-obvious traits an agent cannot infer from the annotations.

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?

Front-loads the purpose, then lays out the discovery workflow, then the variable-filling rules, then the write/retry caveat. Every sentence carries actionable content; no filler or restatement of the name.

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 5-parameter write tool with an output schema, the description covers prerequisites, value formatting, defaults, unsupported cases, and failure handling. Nothing an agent needs in order 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.

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by mapping `request_variables.custom_field_id` to the catalog variable's `id`, requiring `value` to be stringified to match the variable's `kind` (dropdown choices verbatim), and pointing at the right discovery tool for each parameter family. Minor overlap with schema text keeps it below a 5.

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?

Opens with a specific verb+resource ('Submit a SWSD catalog request, creating an incident with `is_service_request: true`') and immediately distinguishes this from a plain incident creation by naming the catalog item path and the prerequisite discovery tools. An agent can tell this apart from `swsd_create_incident` 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit prerequisite chain: `swsd_list_catalog_items` to pick `catalog_item_id`, `swsd_get_catalog_item` to inspect variables, `swsd_describe_custom_fields` before using `custom_fields`. It also states the retry policy (no automatic retry; verify via `swsd_get_incident` first), which is a genuine when-to-do-what instruction.

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

Deploy Server