Duvo MCP

Create Cases

createCases

Create one or more cases in a queue. Provide either a single case object or a cases array (1-100); providing both returns 400. Each case takes a title (max 500 chars), optional labels that will be assigned to the case on creation (missing labels are created on the queue), and an optional priority (none, medium, or high; medium/high raise it above the default in the queue, none is the default; priority only affects the order pending cases are picked up in: due postponed cases are handled first, then higher priority). For the case payload, send free-form data OR a structured json_data object, never both, and a single request must be all free-text or all structured. json_data is validated against the queue's Case schema and requires the queue to have one; a schema-guarded queue accepts only json_data, while a queue without the guard also accepts free-text data. A guarded queue that has no schema yet accepts free-text data only when typed Case schemas are off for that queue — the team has them turned off AND the queue is not inside an automation (there is then no way to declare a schema, so the guard cannot apply). A queue inside an automation always has them on, so a guarded one refuses free-text data until its schema is declared.

Input Schema

TableJSON Schema

Name	Required	Description
`case`	No
`cases`	No
`queue_id`	Yes	The queue's unique identifier

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 9, 2026

addedInput schema / properties / case / properties / json_data

Added value: +{
+  "additionalProperties": {},
+  "description": "Structured payload for a queue that has a Case schema. Validated against that schema and mutually exclusive with `data` — send this instead of free-text `data` on a schema-guarded queue. Within one request, either every case is structured or every case is free-text.",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

addedInput schema / properties / cases / items / properties / json_data

Added value: +{
+  "additionalProperties": {},
+  "description": "Structured payload for a queue that has a Case schema. Validated against that schema and mutually exclusive with `data` — send this instead of free-text `data` on a schema-guarded queue. Within one request, either every case is structured or every case is free-text.",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

First observedAug 17, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The description extensively discloses behaviors: mutual exclusivity of case/cases and data/json_data, label creation on the queue, priority semantics affecting pending order, validation against the queue's Case schema, and the 400 error condition. Annotations already indicate this is a mutating, non-destructive operation; the description adds rich context about validation and side effects, exceeding what annotations provide.

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 long but well-structured, front-loading the core action and then detailing conditions and rules. Every sentence contributes necessary information for the tool's complexity. It could be more concise by trimming some conditional clauses, but the organization is logical and readable.

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?

Given the tool's complexity (nested objects, multiple exclusive modes, schema validation, priority behavior), the description covers all essential aspects: limits, error conditions, data format selection, and queue-specific rules. It doesn't describe return values, but no output schema exists and creation tools typically return minimal info; the description is sufficient for an agent to call it correctly.

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?

Despite only 33% schema description coverage, the description explains the meaning and interaction of all key parameters: the case/cases structure, the 1-100 array limit, the mutual exclusivity of data and json_data, priority enum semantics, and label behavior. This adds substantial meaning beyond the schema's field descriptions, especially for the tricky conditional rules around schema-guarded queues.

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 clear, specific action: 'Create one or more cases in a queue.' This states the verb, resource, and context, and it differentiates from sibling tools like updateCase, deleteCase, and searchCases. The tool's purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

While the description doesn't explicitly contrast with sibling tools, it provides detailed guidance on when to use a single case vs. an array, and when to use free-form data vs. structured json_data based on queue schema guards and automation context. This is strong usage guidance for the tool's own variants, though it omits explicit 'use this instead of X' guidance.

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

All Duvo MCP 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?