auto_fix_layout

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

Annotations already declare destructiveHint=false, openWorldHint=false, and idempotentHint=false, so the safety profile is partly covered; the description adds genuinely new information by stating that repairs are applied automatically and carry 'rollback safety'. However, it does not say what rollback concretely means (the sibling undo tool is never referenced), whether repairs are grouped for a single undo, or what state the scene is left in on partial failure. With annotations doing part of the work, this lands at adequate-but-incomplete.

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?

A single front-loaded sentence with no filler; the verb sequence and defect enumeration are ordered informatively. It is efficient rather than padded, though the density means the rollback claim gets no elaboration.

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?

This is a complex, non-idempotent scene-mutating tool with five undocumented parameters, and the description covers only the purpose and a vague rollback promise. Because an output schema exists, return values need not be explained, but the missing pieces — what dry_run yields, what min_gap controls, how aggressive repairs trade off, and how to undo — are the ones an agent needs before invoking it.

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% across five parameters, so the description carries the full burden and does not meet it. The defect list loosely maps to the repair_scope enum values (overlaps, text/connectors, containment, spacing), but dry_run, min_gap, aggressiveness, and especially name receive no explanation at all — min_gap's unit and aggressiveness's behavioral trade-off are exactly the kind of detail the schema lacks.

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 concrete actions (diagnose, plan, repair) and an explicit resource (layout defects) with a parenthetical enumeration of defect classes: overlaps, text clipping, containment, routing, spacing. This clearly distinguishes it from siblings like move, resize, or update_element, which alter elements individually rather than auto-repairing layout. It stops short of 5 because it never states the operating scope (scene-wide vs. selected elements), which is the main ambiguity against those siblings.

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?

There is no when-to-use guidance: nothing says whether this should be run instead of manual move/resize fixes, whether it must follow get_scene or describe_scene, or when to prefer preview or undo. The presence of a dry_run parameter is not acknowledged, so the natural safe-first workflow is left entirely implicit. An agent must infer the workflow from parameter names alone.

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