Project new

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: it itemizes the state destroyed (geometry, evacuation, sprinkler, HVAC, drawing), documents the refusal guard, and warns that discard_unsaved discards edits and should be user-confirmed.

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 operative content is front-loaded in two compact sentences with no filler. The trailing rule-ID citations are slightly noisy but serve as pointers to referenced governance rules rather than wasted prose.

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 one-parameter, no-output-schema mutation tool this covers purpose, side effects, guards, and safety. It stops short of describing the post-reset state or return value, a minor gap given the tool's simplicity.

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 already 100% (default false is documented in the schema), so the baseline is 3; the description adds real meaning by explaining the refusal semantics the flag overrides and the consent requirement for using it.

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 and resource ('Start a new empty project in the running app (File > New)') and enumerates exactly what state is cleared, which cleanly separates it from siblings like project_open, project_save, and shape_new_document.

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 a clear usage condition ('Live app only') and an explicit pre-condition with the remedy (refuses with unsaved changes unless discard_unsaved=true). It does not name an alternative tool for the non-live/headless case, so routing to a sibling is left to inference.

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