Preview per-tile metadata updates

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

Annotations already declare readOnlyHint=true, so no contradiction. The description adds value by detailing what is and isn't touched (e.g., 'tile geometry, atlas images, and referencing maps are never touched') and noting that removeCollectionTile is destructive and removing last entry fails closed. This exceeds annotation coverage.

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?

The description is a single dense paragraph that packs substantial information but lacks structural breaks (e.g., bullet points or sections). While every sentence adds value, the length and flow reduce scanability. Moderate conciseness.

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 the tool's complexity (6 parameters, nested update variants, conditional behavior for embedded vs external tilesets) and the presence of an output schema, the description fully covers when to use each parameter type, behavioral constraints (e.g., 'removing the last entry fails closed'), and distinction between external and embedded. No gaps are apparent.

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 coverage is 50%, but the description adds meaning beyond schema: explains that embeddedIndex replaces tilesetAssetId for inline tilesets, that expectedTilesetRevision is omitted in that case, and that createCollectionTile requires a verified project image and pins pixel size. These details help the agent use parameters correctly.

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 title 'Preview per-tile metadata updates' and description explicitly state it validates and returns a change set without modifying assets. The description clearly distinguishes between external and embedded tilesets, and what types of updates it handles (probability, class, animation, properties, collision, and structural collection updates). This is a specific verb-resource combination with clear 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?

The description provides context for when to use embeddedIndex vs tilesetAssetId, and when structural updates are possible (image-collection tilesets only). However, it does not explicitly state when to prefer this tool over other preview tools like tiled_preview_edits, nor does it list alternatives or exclusions.

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