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

Annotations already cover the read-only/idempotent/no-destruction profile, and the description adds genuinely new context: it never writes, never calls a paid provider, and operates against the current owned revision. It also explains what the response can carry (layout_warnings) and what causes them (cards sticking out of frames or overlapping), which goes beyond the annotations.

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 tight sentences with the core action and the no-write guarantee front-loaded, then the warning-and-retry loop. The jargon in sentence one and the capabilities cross-reference are dense but each still carries information; little is wasted.

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?

With no output schema, the description takes on the burden of describing the return, and it does by naming layout_warnings and its meaning. The remaining gap is the revision parameter semantics, which matter for a preview-against-a-revision tool.

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 carry the load, and it only partially does: it explains where operations come from (capabilities) and implies revision handling, but project_id and expected_rev are never addressed. 'Uses current owned revision' is also ambiguous given that expected_rev is a required caller-supplied parameter.

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 ('Preview draft edits') and scopes it to the layout_composition planner with measured cards, group frames, and diagnostics, which is clearly distinct from the sibling aimixer_canvas_apply. The clause 'the ONE canonical layout_composition planner' is internal jargon that adds noise rather than precision, keeping it just short of a 5.

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 in the workflow: preview here, fix operations on layout_warnings, then apply, and it points to aimixer_canvas_capabilities as the source of valid operations. It gives clear context without naming explicit exclusions for the other ~60 siblings.

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