document_new

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

With no annotations, the description carries the burden and does a good job: it discloses the active-state effect, the persistence gap (not saved until document_save), and the display-vs-model unit gotcha. It omits what happens to the previously active document and whether unsaved work is at risk, which for a document-lifecycle tool would be useful.

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?

Front-loaded with the core action and side effect, then the save caveat, then the units caveat, then return value. Every sentence adds a distinct fact; the worked example is short and reinforces defaults.

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?

No output schema exists, and the description compensates by pointing to document_list for the returned shape. Combined with the save and units guidance, an agent can call this correctly; only the fate of the previously active document is unaddressed.

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 the baseline is 3, but the description earns above baseline by clarifying that `units` affects only display while tool inputs stay in mm — a non-obvious behavior the schema text ('Distance display units of the design') does not convey. `design_type` is left entirely to the schema, which already explains parametric vs direct.

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 ('Create a new design document') plus the side effect ('make it active'), which distinguishes it from document_open/document_activate. The agent knows exactly what it gets without reading the schema.

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 routes the agent: the document is NOT saved, and document_save should be called only when the user asks to save. This is a real when/when-not rule tied to a named sibling. It stops short of contrasting with document_open or document_activate, which remain inferable only from the name.

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