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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the meaningful behavioral fact that it writes nothing and that creation needs an external CLI, which goes beyond the annotations' safety profile.

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?

Two tight sentences: the first lists what the preview shows, the second clarifies the no-write behavior and points to the CLI. Front-loaded and zero waste.

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 read-only preview with full schema coverage and safety annotations, the description covers purpose, scope, and the key no-write constraint. It omits return-shape details, but with no output schema that is a minor gap given the preview nature.

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%, with each parameter richly documented, including conditional rules like platform being required for multi-platform workflows and enableOfflineId's defaulting behavior. The description adds no parameter-level detail beyond the schema, so the baseline 3 is appropriate.

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 (Preview) and resource (Offline Protocol starter), and enumerates its contents (workflow, template, packages, file list). Clearly distinguishable from siblings like get_template or generate_architecture, which retrieve or generate rather than dry-run preview.

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?

Explicitly frames this as a dry run that writes nothing, and notes that actually creating the project requires the local CLI instead. This effectively tells the agent when this tool applies vs. a create action, though it doesn't reference sibling preview/listing tools.

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