preview_drawing_plan

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

With no annotations, the description carries full burden and does disclose several real traits: non-mutating, capped at 100 operations, and returns a planId. It says nothing about what validation failures look like, error semantics, permissions, or plan expiry, which are the remaining behavioral gaps for a mutation-adjacent tool.

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?

Two tight sentences with the non-mutating guarantee and the 100-op cap front-loaded, followed by the return contract. Nothing is padded and every clause earns its place.

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?

Given a deeply nested anyOf schema with seven operation types, no annotations, and no output schema, the description supplies the essentials: what it validates, that it does not mutate, the operation cap, and that a planId is returned for commit. Missing only error/validation-result semantics, which is a modest gap.

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% for the single complex param, so the description must compensate. It partially does by naming the operation families (geometry, text, dimension, layer) that map onto the schema's anyOf variants, but adds no syntax or field-level meaning for line/polyline/circle/rectangle dimensions.

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 specific verbs (validate, preview) and the resource (drawing operations), and enumerates the operation domains covered (geometry, text, dimension, layer). It clearly implies a two-phase pattern with commit but never names the sibling apply_drawing_plan, so an agent infers rather than reads the distinction.

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?

'without changing the drawing' plus 'Returns a planId for explicit commit' implies this is the pre-commit step in a two-phase workflow, which is useful. However it never explicitly names apply_drawing_plan as the follow-up or states when to skip the preview, leaving the routing to inference.

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