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, and it does well by disclosing templates, output behavior ('Result includes the CLI output and a Next steps section with `docs_search` queries'), and the wrapper nature. However, it lacks details about failure conditions such as behavior if the target directory already exists or if names are invalid beyond the snake_case note. This is a minor gap but not misleading.

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 concise yet information-dense, with each sentence serving a purpose: purpose, wrapper context, usage triggers, template details, and return value. It is well-structured and front-loaded with the core action, making it easy for an agent to parse quickly. No filler or redundant phrasing.

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 no output schema, the description adequately covers expected results ('CLI output and a Next steps section'). It also provides enough context about templates and naming to make the tool usable without external knowledge. The description fully compensates for missing structured metadata, making it complete for its complexity.

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?

The input schema already has 100% coverage, but the description adds significant semantic value. It elaborates each template with concrete contents (e.g., 'research' includes 'notebook + sample data + main.py') and clarifies that `project_name` special characters become snake_case in `__PROJECT_SLUG__`. This goes beyond the schema's minimal descriptions and helps an agent select appropriate values.

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 opens with a specific verb+resource statement: 'Create a new FLOX project from a bundled template.' It also notes this is a 'thin wrapper around the canonical `flox new` CLI', which clarifies its limited scope and distinguishes it from the broader `flox` CLI and sibling tools like `scaffold_strategy`. The purpose is immediately evident.

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 explicitly states when to use the tool with concrete user intents: 'Use when the user asks "set up a new flox project" / "I want to scaffold a research notebook" / "start a live trading bot".' This provides clear invocation criteria. It also mentions that the CLI remains the source of truth, implying the MCP tool is for discoverability and simple use cases, which guides the AI agent toward the appropriate pathway.

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