list-tiles

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

With no annotations, the description carries full burden. It explicitly states 'Read-only' and discloses the important coordinate conversion detail (top-left canvas pixels vs v14's center-anchored coords). It also lists all fields returned, which is transparent about the output. Minor gaps like error behavior are not critical for a list operation.

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 sentence that front-loads the core action ('List every Tile') then enumerates fields and the conversion note. Every clause adds value; there is no filler. It could be slightly restructured for readability, but it remains concise and well-ordered.

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?

For a simple one-parameter list tool with no output schema, the description provides all needed call context: what is returned, the coordinate transformation, the read-only nature, and the intended workflow. It does not describe the exact response structure, but the field list compensates.

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 100% for the single parameter (sceneIdentifier has a description: 'Scene id or exact name holding the placeables.'). The description adds no additional parameter semantics beyond reinforcing 'on a scene', so a baseline 3 is appropriate.

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 verb and resource: 'List every Tile on a scene' followed by an exhaustive enumeration of returned fields. It clearly differentiates from sibling list tools (list-tokens, list-walls) by targeting tiles and naming update-tiles/delete-tiles as its follow-up operations.

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 explicitly positions the tool as 'the inspect step before update-tiles / delete-tiles', telling the agent when to use it (before edits) and that it's read-only. It does not explicitly contrast with other list tools, but the naming of the exact sibling pair provides clear context.

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