preview_alignment

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

With no annotations, the description carries the load and does well: it declares read-only semantics ('without changing the document'), an output artifact ('native PNGs'), and a cleanup side effect ('removes all temporary scene-graph overlays afterwards'). It stops short of saying how the PNGs are delivered (paths vs. inline) or what happens on failure mid-cleanup.

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 promise and no wasted sentences; the no-mutation guarantee is repeated as a closing clause for emphasis. The 'cyan ghost + green/orange axes' fragment is jargon-dense but conveys the visual output efficiently.

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 tool with no annotations, an undocumented 'size' parameter, and no output schema, the description is adequate but not whole. It covers behavior and side effects well yet leaves the agent guessing about image dimensions/resolution semantics and how the produced PNGs come back.

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 0%, so the description must compensate. It hints at plan_id constraints ('fresh and unapplied') but never explains the identifier's origin or format, and the 'size' parameter is never mentioned at all, leaving one of two parameters completely opaque.

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 ('See the proposed placement') and immediately bounds the scope ('without changing the document', 'Does not add document objects or move parts'). It implicitly separates itself from a committing sibling, though it never names apply_alignment, so differentiation relies on inference.

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 real precondition: 'The plan must be fresh and unapplied', which tells the agent when this call is valid and implies it precedes an apply step. It does not explicitly name apply_alignment as the alternative or say what to do if the plan has already been applied.

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