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

Discloses significant behavior beyond annotations: creation is atomic with rollback on partial Audience failures; Studies are private by default; enabling link sharing publishes attached Audiences and Minds at world-readable URLs; follow-up research does not require a new Study. These are safety-relevant and privacy-critical details not visible in 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?

The description is a bit dense and could be better structured with paragraphs, but every sentence earns its place: purpose, research-block guidance, direct-question rule, atomicity, and privacy caveats are all material. The critical privacy warning is near the end, which is slightly suboptimal, but the overall length is justified by the rules-heavy nature of the tool.

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 creation tool with no output schema, the description covers the essential contexts an agent needs: when to create a Study, how to batch research questions, legacy vs preferred parameter fields, atomic rollback behavior, and privacy side effects. Sibling tools for finding Audiences and Minds are referenced (list_audiences/list_minds) inside the schema, giving the agent a clear workflow.

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 100%, so structured descriptions already document every parameter. The description adds value by emphasizing that audienceConfigs is the preferred field over groupConfigs/groupIds legacy aliases, and it reinforces the privacy implications of isLinkSharingEnabled beyond the schema's warning.

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's function: 'Creates a new Study workspace from existing Audiences or inline Audience configurations.' It explicitly contrasts itself with related operations ('it does not ask questions or run research') and distinguishes Study creation from follow-up research, making it easy for an agent to differentiate from siblings like ask_study, plan_study_questions, and run_study_questions.

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?

Provides strong when-to-use guidance: tells agents that any multi-question set belongs in a planned block inside a Study, never as separate direct questions, and that a direct question is only appropriate for a single standalone question or dependent follow-ups. It also warns against enabling link sharing unless explicitly requested, which is critical usage guidance.

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