new_row

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

Annotations only declare readOnlyHint=true. The description adds meaningful behavior beyond that: the row is responsive and auto-collapses (tablet 2, mobile 1) to prevent cramped cards, and it returns a node to be placed elsewhere rather than mutating state directly. No contradiction with the read-only hint.

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-loads the core concept and integration instruction in the first sentence. Uses ALL-CAPS emphasis and a couple of bold phrases that add slight visual noise, but every sentence carries information and there is no filler.

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 noting the return value is a node to be placed inside a section. Combined with the responsive/collapse behavior and the child-shape example, an agent has enough to invoke it correctly, though richer guidance on composing the returned node with sections would round it out.

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 description coverage is 100%, so row_gap, collapse, col_widths, column_gap and container_opts are already fully documented in the schema. The description adds an example children array, which is marginally useful for the nested children param, but it does not explain the gap/collapse/width parameters beyond what the schema provides, so the baseline of 3 applies.

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 ('Build a multi-column ROW container') and immediately contrasts the layout semantics against its sibling concept ('children laid out SIDE BY SIDE (not stacked)'). The distinction from column/stacked layout lets an agent tell it apart from new_section and new_element without opening either 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?

Gives concrete use cases (feature cards, category tiles, footer columns, 2-col hero) and an explicit integration rule: place the returned node as a child inside a section, and nest a row for horizontal layout because section children stack vertically. Clear when-to-use context, though it does not name sibling tools like new_section or new_element explicitly.

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