start_project

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

With no annotations provided, the description must carry the burden of behavioral disclosure. It does disclose that the tool mutates state ('Creates state'), returns interview questions, and that code should not be written yet. However, it does not explain persistence, failure modes, idempotency, or what happens if the project already exists, so the transparency is only partial.

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 short, front-loaded with the primary purpose, and every sentence adds value. It states what happens, what to do next, and what not to do, all in three concise sentences with no filler.

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 a simple two-parameter tool with no output schema or annotations, the description covers the core workflow reasonably well. However, the absence of parameter explanations and the lack of guidance about when this tool should be called relative to siblings like submit_answers leaves notable gaps for an agent making a fully informed call.

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, and the tool description does not explain what 'brief' or 'repo_path' should contain. The parameter names are suggestive, but the description adds no meaning beyond the schema, leaving the agent to guess the required format and semantics.

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 a specific action and resource: 'Begin a design-first project,' and it concretely says the tool 'creates state and returns the first interview questions.' This distinguishes it from siblings like make_plan, run, and approve_plan, which are later workflow steps.

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?

It gives clear context: this is the first step of a design-first project and returns interview questions for the user. It also instructs the agent to ask the user these questions and explicitly says 'do NOT write code yet,' which helps with when-not behavior. It does not name alternatives like submit_answers, but the workflow context is clear.

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