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 explains that project_dir is created if missing, errors if spec.yaml already exists, and details how name and state_fields are used. It does not mention whether other files are overwritten or permissions required, but the error condition on spec.yaml suggests safe creation. This is reasonably transparent for a scaffold tool.

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 compact and front-loaded with the core purpose, followed by parameter explanations. Each sentence carries necessary information—creation artifacts, error condition, and parameter details. It is slightly verbose in the parameter block but remains efficient and well-structured.

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?

For an initialization tool with an output schema (not shown), the description covers all necessary aspects: purpose, parameters, error behavior, and file outputs. It does not mention what the return value looks like, but since an output schema exists, that is acceptable. It could be more explicit about side effects (e.g., creating directories) but overall it is complete for correct invocation.

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 schema has 0% description coverage, so the description must fully compensate. It does: each parameter (project_dir, name, state_fields) is explained with its role, constraints, and expected structure (e.g., state_fields items have name, type, reducer?, default?). This adds meaning far beyond the bare schema titles.

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 tool creates a new spec-driven LangGraph project and enumerates the artifacts it generates (spec.yaml, nodes.py stub, __init__.py). This distinguishes it from sibling tools that modify or inspect an existing project, so an agent can immediately recognize it as the setup/initialization tool.

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 implies usage for new projects by noting that an error occurs if spec.yaml already exists, which effectively warns against reuse. However, it does not explicitly state when to prefer this tool over siblings (e.g., 'use for initial scaffolding') or mention any alternatives. The error condition provides partial guidance but the exclusion logic is left implicit.

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