tileset

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly carried elsewhere. The description adds a genuinely useful domain fact ('Tile index 0 is the empty tile') and hints at return shape for get_tile, but never says what delete/delete_tile destroy, whether indices shift after deletion, or how batch mode differs — and with the schema covering 'save' and 'backend', a 3 is appropriate.

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 dense sentence, front-loaded with the action list, with no filler. It is compressed almost to telegraphic style, which costs some readability for a 15-parameter dispatcher but wastes no words.

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 an 8-action, 15-parameter tool with no output schema, the description covers action/parameter associations and get_tile's return shape, which is the minimum viable. It omits what 'list' returns, the effect of delete on tile indices, and per-action return values for the remaining actions.

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?

With only 40% schema description coverage across 15 params, the description does real work by binding parameters to actions — 'add (tileSize, count)', 'update (name, baseIndex, data)', 'set_tile (rows+legend or an image file)'. Undocumented params (index, properties, sprite, tileset, file) are never explained, but the action-to-parameter mapping is the critical missing piece and it is supplied.

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 the resource (tileset) and enumerates all eight actions it dispatches, so an agent knows this is the tileset CRUD tile-manipulation surface. It is clear, but it never distinguishes itself from the sibling 'tilemap' tool, which plausibly overlaps in 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?

There is no when-to-use guidance: no statement of when to pick this over the sibling 'tilemap' tool, no note that 'action' selects the operation, and no exclusions. The action list is a menu, not usage advice.

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