cocos_init_project

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it copies a template, patches `package.json` with a UUID and version, and creates `assets/` subdirectories. However, it lacks details on error handling, permissions required, or whether the operation is idempotent, which are important for a tool that writes to the filesystem.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the main purpose, followed by specific actions and a usage guideline. Each sentence adds value: the first states the overall goal, the second details the steps, and the third provides prerequisite advice. There is no wasted text, and the structure is logical and efficient.

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

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

Given the complexity of initializing a project with 4 parameters, no annotations, and no output schema, the description does a good job covering the core functionality and usage. It explains what the tool does, key parameters, and a prerequisite step. However, it lacks information on output (e.g., success confirmation or error messages) and does not fully document all parameters, leaving some gaps in completeness.

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

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

Schema description coverage is 0%, so the description must compensate. It explains the purpose of `dst_path` (where the project is copied), `creator_version` (patched into `package.json`), and `template` (default is 'empty-2d'). It does not mention `project_name`, leaving one parameter undocumented, but provides meaningful context for three out of four parameters, which is substantial given the lack of schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Initialize a new Cocos Creator project from a template') and resource ('Cocos Creator project'), distinguishing it from siblings that focus on adding components, managing assets, or building projects. It explicitly mentions copying a template, patching files, and creating directories, which differentiates it from other initialization or creation tools in the list.

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

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

The description provides explicit guidance on when to use this tool: 'Use `cocos_list_creator_installs` first to see available versions.' This indicates a prerequisite step and suggests an alternative tool for checking versions, helping the agent understand the proper sequence and context for invocation.

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