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

Annotations already declare it a non-destructive write, but the description adds meaningful traits beyond them: the artifact stays a DRAFT, it surfaces on the Studies page, generation consumes inference credit (a real cost signal), and it may return `needs_confirmation`. The confirmation flow is only hinted at, not explained, so it falls short of a 5.

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?

Purpose is front-loaded in the first clause, with supporting detail following efficiently. Slightly dense with em-dash asides and a parenthetical cross-reference, but every sentence carries information useful to an agent.

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 no output schema and three parameters, the description shoulders more burden; it does well by explaining the created draft's lifecycle, cost, and the possible `needs_confirmation` response. The one gap is the unexplained `approvalId` parameter and no hint of the success response shape.

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 67%: `about` and `workspace` are documented in the schema, but `approvalId` is not, and the description never mentions any parameter by name. The 'May return needs_confirmation' line vaguely gestures at the approval flow that `approvalId` presumably serves, but the connection is never made explicit.

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?

States a specific verb+resource ('Generates and creates a DRAFT study') and its defining constraint ('isn't tied to any canvas node'), which cleanly separates it from the sibling prism_studies_draft and prism_studies_draft_from_interviews. Concrete examples (brand tracking, workspace-level research) reinforce the scope.

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?

Gives clear conditions for use — 'anything you can describe in a sentence' and explicitly not tied to a canvas node — which routes the agent away from the canvas-bound draft sibling. It stops short of naming the alternative to use when a canvas node IS involved, so it is strong context without explicit when-not/alternative routing.

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