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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is largely covered. The description still adds genuine value by stating it uses the current owned revision and never calls a paid provider (a cost/side-effect guarantee not in the annotations), plus the layout_warnings remediation loop. It does not describe the rest of the result payload beyond warnings.

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?

Four sentences, front-loaded with the purpose and the no-write/no-paid-provider guarantee before the warning-handling instruction. Dense but each sentence carries information; only the 'ONE canonical layout_composition planner' clause is padding.

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 and 0% parameter coverage, the description should carry more weight. It covers the operations source and the layout_warnings return path, but leaves project_id/expected_rev semantics and the remainder of the preview result undocumented, which is thin for a 3-required-param tool with an opaque operations array.

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 for three required parameters. It partially does: 'uses current owned revision' hints at expected_rev's optimistic-concurrency role and 'operations come from aimixer_canvas_capabilities' points at the operations format. project_id is entirely unexplained and no operation shape or revision-mismatch behavior is given, so the gap is only half closed.

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?

The description names a specific verb ('Preview draft edits') and enumerates what the preview computes: measured cards, near-square group-frame grid, collision/viewport diagnostics. It implicitly separates itself from aimixer_canvas_apply ('before apply') and from aimixer_canvas_inspect_layout, though it never names a sibling directly. The 'ONE canonical layout_composition planner' phrasing is jargon-heavy but still conveys scope.

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?

It establishes the workflow context clearly: preview before apply, fix operations and re-preview on warnings, and source operations from aimixer_canvas_capabilities. That is real routing guidance. It stops short of explicit when-not-to-use conditions or naming apply/inspect_layout as the alternative endpoints.

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