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

Annotations declare readOnlyHint=true and the description is fully consistent with a read operation. Beyond that it explains domain semantics the annotations cannot convey: Inbox scenes are not in any tab yet and carry a suggested tab derived from their project path, and the duplicate-creation hazard makes the read a prerequisite. It stops short of noting result size, pagination, or behavior when nothing has ever been synced.

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?

Front-loaded with the return payload, then the when-to-use guidance and the sibling handoff; every sentence earns its place. The parenthetical about suggested tabs is dense but necessary, and the single-block paragraph is slightly run-on.

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 an output schema covering return values and annotations covering safety, the description supplies the missing usage and domain context well. The only material gap is that the sole required parameter is never explained.

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?

Only one parameter, game_id, and schema coverage is 0%, so the schema adds no meaning. The description implicitly frames the result as scoped to 'the game' but never states what game_id accepts or how to obtain it (for example list_games).

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 states a specific resource (engine-synced scenes) and enumerates exactly what the read returns: last sync time, inbox scenes with suggested tabs derived from project paths, and scenes already promoted to entities with their folder. It is clearly distinguishable from siblings like place_scenes, create_entity, and sync_scenes.

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 gives explicit when-to-use triggers (after the user clicks Sync to confirm it worked; before creating entities by hand to avoid duplicating a synced scene) and routes to a specific alternative (place_scenes) when the Inbox is non-empty. Nothing is left to inference.

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