kernel_projects_create

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

With no annotations, the description carries the full behavioral burden, but it discloses almost nothing: not whether creation is irreversible, what happens on slug collision, what permissions are needed, or what the call returns. The only behavioral detail is that value_prop and audience must be present.

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 short sentence, front-loaded with the action and the key constraint in parentheses. Nothing is wasted, though the brevity contributes to the gaps noted elsewhere rather than being purely 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?

For a three-required-parameter mutation with a nested brief object, no annotations and no output schema, an agent still cannot tell what fields may go into the brief beyond the two required ones, whether slug formatting matters, or what comes back. The definition is too thin for the tool's structural 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?

Schema coverage is only 33%, but the description does add real information beyond the schema by stating that value_prop and audience are required inside the brief, which the schema's '{ value_prop, audience, markets?, ... }' notation leaves ambiguous. It says nothing about the semantics or format of slug and name, so it only partially compensates for the coverage gap.

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 gives a specific verb ('Create') and resource ('project') and identifies the payload it takes ('with its brief'), which is enough to distinguish it from the agent/office siblings. It stops short of explaining how this differs from other creation endpoints or what a project object represents.

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?

There is no guidance on when to use this tool versus alternatives, no prerequisites (for example whether the slug must be globally unique or unique within an org), and no follow-up steps such as assigning an office via kernel_projects_assign_office. Usage is only implied by the verb.

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