Flower MCP

Overview Schema Source Related Servers Discussions Admin

fow_create_project

Idempotent

Creates a unique local lifecycle project authority before recording requirements, goals, or implementation work, rejecting duplicate project IDs.

Instructions

Register a uniquely identified local lifecycle project before recording its requirements, goals and implementation work. This creates lifecycle authority rather than repository scaffolding. Single operation; call directly without an operation argument. Prerequisites: Choose a unique lifecycle project ID and human-readable name. Effects: Creates canonical local project authority and its audit event. Repeated creation of the same project_id rejects before further effects; request_id is inert. Does not inspect or create repository files. Exact help (replace operation_name with the selected route): fow_capabilities({"view":"operation","operation_tool":"fow_create_project","operation_name":"call"}).

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": {
      "project_id": "<project_id>",
      "name": "<name>",
      "actor": "<actor>"
    },
    "name": "fow_create_project"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Human-readable project or milestone name.
`actor`	Yes	Identity of the human or agent recording this action; retain the original identity when replaying its request.
`project_id`	Yes	Canonical lifecycle project ID. Select the existing project explicitly; development Markdown authorities are separate from runtime projects.
`request_id`	No	Accepted compatibility input; current project creation does not consume request_id or issue a request replay receipt. The canonical project_id is unique and identical repeated creation is rejected before adding effects.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.5.1Oct 16, 2026

addedInput schema / properties / actor / description

Added value: +"Identity of the human or agent recording this action; retain the original identity when replaying its request."

addedInput schema / properties / name / description

Added value: +"Human-readable project or milestone name."

addedInput schema / properties / project_id / description

Added value: +"Canonical lifecycle project ID. Select the existing project explicitly; development Markdown authorities are separate from runtime projects."

addedInput schema / properties / request_id / description

Added value: +"Accepted compatibility input; current project creation does not consume request_id or issue a request replay receipt. The canonical project_id is unique and identical repeated creation is rejected before adding effects."

First observedv0.1.0Oct 16, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare non-readOnly, idempotent, non-destructive and closed-world, and the description adds real depth beyond them: duplicate project_id is rejected before further effects, request_id is inert, an audit event is created, and repository files are neither inspected nor created. This is exactly the behavioral context an agent needs before invoking a state-mutating tool.

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?

Purpose is front-loaded and the remainder is organized into usable Prerequisites/Effects clauses with zero filler sentences. The trailing 'Exact help' boilerplate and some conceptual jargon slightly dilute an otherwise tight passage, keeping it just short of 5.

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?

An output schema exists, so return values need not be explained. Given that, the description covers purpose, prerequisites, side effects, duplicate-rejection behavior and non-file-system scope — everything needed to call it correctly.

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

Parameters3/5

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; each parameter already has its own description in the schema. The description reinforces project_id uniqueness and request_id inertness, but that duplicates what the schema fields (particularly request_id) already document, so it adds little beyond the structured data.

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?

States a specific verb+resource ('Register a ... local lifecycle project') and immediately scopes it ('lifecycle authority rather than repository scaffolding'), which separates it from repo-file creation and from downstream siblings like fow_register_requirement and fow_goal. An agent can tell what this does and where it sits in the sequence 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 Guidelines4/5

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

Explicitly says 'Single operation; call directly without an operation argument' and lists prerequisites (pick a unique project_id and human-readable name). It gives clear conditions for use but does not route to a named alternative tool (it only points at fow_capabilities for help), so full when/when-not/alternatives coverage is not reached.

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