Skip to main content
Glama
Sign In

Frostbyte

by dev.getfrostbyte
OverviewDiscussionsAdmin

create_project

Create a new Frostbyte project owned by you, with you as its only member. Call it only when the user explicitly asks for a new project, and check list_projects first so you don't duplicate one they already have; to change an existing project use update_project. Not idempotent: each call creates another project. Counts against the user's plan project limit; if the limit is reached, tell the user rather than retrying. Returns the new project ID; follow with create_area or create_task only for what the user agreed.

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

Input Schema

NameRequiredDescriptionDefault
nameYesProject name, usually the product's name. Max 30 characters; must not be blank.
contextYesExplain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."
descriptionNoOne-line pitch: what the product does. Longer text is cut at 150 characters. Omit if the user hasn't said.
productStageNoWhere the product is in its lifecycle (default: idea). "idea" starts with the User Signals module turned off; the other stages turn it on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / description / description
      Previous value: -"One-line pitch: what the product does (max 150 chars)."New value: +"One-line pitch: what the product does. Longer text is cut at 150 characters. Omit if the user hasn't said."
    • changedInput schema / properties / name / description
      Previous value: -"Project name — max 30 characters."New value: +"Project name, usually the product's name. Max 30 characters; must not be blank."
    • changedInput schema / properties / productStage / description
      Previous value: -"Where the product is in its lifecycle (default: idea)"New value: +"Where the product is in its lifecycle (default: idea). \"idea\" starts with the User Signals module turned off; the other stages turn it on."
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare idempotentHint=false and destructiveHint=false, but the description goes further: it explains the consequence of non-idempotency ("each call creates another project"), discloses a plan-limit constraint with a failure policy (tell the user rather than retry), and states what is returned (the new project ID). That is exactly the kind of operational context annotations cannot express.

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?

Four compact clauses covering what it does, when to call it, what to check first, failure behavior, and return value, with the core action front-loaded. No filler or restatement of the title.

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 creation tool with no output schema, the description supplies the return value, the non-idempotent side effect, the limit failure mode, and the recommended follow-up. An agent has everything needed to call it and to handle its outcomes.

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 all four parameters including the productStage enum effects are already documented at the field level. The description adds no additional meaning about parameters, so the baseline of 3 applies.

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 and resource ("Create a new Frostbyte project") and immediately scopes ownership and membership ("owned by you, with you as its only member"), which no sibling name conveys. It is unmistakably distinct from update_project, get_project, and the create_area/create_task siblings.

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?

States an explicit precondition ("only when the user explicitly asks"), a mandatory pre-check ("check list_projects first so you don't duplicate"), and the alternative for the other case ("to change an existing project use update_project"). It also tells the agent not to chain into create_area/create_task unasked, which is when-not-to-use guidance at a granular level.

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

All Frostbyte toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources