Vilix AI

create_project

Create a new project. title is required; description is one line (the goal). project_rules is markdown inherited by all tasks — stack/conventions/tone.

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": {
      "title": "<title>"
    },
    "name": "create_project"
  }
}

Input Schema

Name	Required	Description	Default
`title`	Yes
`description`	No
`project_rules`	No

Output Schema

Name	Required	Description	Default
`error`	No
`inbox`	No
`message`	No
`project`	No
`instruction`	No
`upgrade_url`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 5, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already indicate this is mutating and not idempotent, so the description need not restate that. It adds useful context about how project_rules propagates to tasks, but it does not disclose persistence effects, error conditions, or any side effects beyond creation. This is acceptable for a simple create tool but not richly transparent.

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?

Three brief sentences with no filler. The main action is front-loaded, and each subsequent sentence addresses one of the two optional parameters. Every clause contributes meaning.

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

Completeness4/5

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

For a simple creation tool with three parameters and an output schema present, the description covers the required and optional parameters adequately. It lacks an explicit pointer to update_project for existing projects, but that is a usage distinction rather than a missing operational detail needed to invoke this tool correctly.

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 0%, so the description carries the full burden. It compensates well: title is marked as required, description is explained as a one-line goal, and project_rules is given concrete meaning as markdown covering stack/conventions/tone inherited by tasks. It does not elaborate on nullability or format constraints, but the schema already displays defaults.

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 'Create a new project,' naming an explicit action and resource. It is distinct from sibling tools like create_task and update_project by clearly targeting project creation, and the following sentences specify what counts as a project (goal plus inherited rules).

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?

The word 'new' implies this is for creation rather than updates, and the note that project_rules is inherited by tasks suggests when project-level context is needed. However, no alternative tools are named and no explicit when-not-to-use guidance is given, so selection among siblings is largely 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 Vilix AI 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?