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

Annotations only declare it is a non-readonly, non-idempotent, non-destructive write. They do not disclose the two-stage gate where a `planning`-less call returns the questions and makes nothing — a non-obvious, high-impact behavior buried entirely in a nested schema field. The description adds essentially no behavioral context beyond the annotations.

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?

A single front-loaded sentence with no filler, which is good structurally. However, at this length it is under-specified rather than genuinely concise — the brevity comes at the cost of omitting the planning gate and the name/imagery parameters.

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?

With 5 parameters, a nested `planning` object, 0 required fields, and no output schema, the description needs to explain the creation workflow and what happens on a planning-less call. It does neither, leaving an agent unable to call this correctly from the description alone.

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?

Coverage is only 60%; `name` and `imagery` have no schema descriptions at all, and the description does not compensate for either. The one thing the description does cover (kind) is already fully explained in the schema, so it adds no meaning beyond structured data.

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 verb and resource are clear ("Start a project") and the kind values are disambiguated with examples. But the single most important fact about this tool — that calling it without `planning` creates nothing and instead returns questions — is absent, so an agent reading only the description would misjudge what the call actually does. It also doesn't distinguish itself from siblings like open_project or list_projects.

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?

No indication of when to use this rather than open_project (existing project) or list_projects. The required prerequisite — supplying `planning` before the first project — is never stated in the description, so an agent has no routing or sequencing guidance from the text.

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