plan_screen_architecture

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

With no annotations the description carries the full burden, and it does well: it discloses that this is a planning step that yields a roadmap, and that executing canvas mutations must wait for user confirmation. The 'guarantee zero overflow/overlap' claim is aspirational rather than a verified behavior, and it never states outright that the tool itself performs no mutations.

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?

Three front-loaded sentences that each carry weight: purpose, decomposition detail, then the mandatory protocol gate. Slightly dense but no filler, and the most important operational constraint is placed last where it stands out.

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 nine-parameter tool with nested objects and no output schema, the description covers the intent, both modes and the post-call protocol. The one real gap is that it references a 'generated roadmap' without describing that return structure, which matters since no output schema exists to fill it in.

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 the schema already documents all nine parameters, enums and nested shapes; baseline is 3. The description adds only framing (create vs edit, 8pt grid multiples, wrapping/stretch constraints) that loosely maps to existing fields but no parameter syntax or format detail beyond the schema.

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 pair (architect/plan) plus resource (multi-section UI screen, or edit/refactor) and enumerates the concrete outputs it produces: ordered steps, typography scale, 8pt grid, layout constraints. An agent can distinguish this planning tool from the canvas-mutation siblings without opening 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 positions the tool 'before code generation' and as a gate prior to canvas mutations, and it distinguishes create vs edit usage. It does not, however, name alternative siblings (create_frame, set_autolayout) or state when this tool should be skipped, so it stops short of full when/when-not routing.

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