Paint tiles

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

With no annotations, the description carries the full behavioral burden and does substantial work: it decodes layer semantics (0-3 tile layers, 4 shadow bits, 5 region ids), the MZ slot-to-layer mapping, and the key trait that painting on a wrong layer 'still renders, only at the wrong depth, so the reply says so'. It omits permissions/auth, idempotency, and undo interaction, so not a 5.

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 purpose is front-loaded and the sentences are information-dense, each adding layer rules or behavior. The 'forest vs a field of trees buried under the grass' metaphor is vivid but somewhat verbose, making the paragraph longer than strictly necessary.

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 mutation tool with no annotations and no output schema, the description supplies the essential context an agent needs: layer model, auto-layer inference, and the wrong-layer side effect. It is nearly complete, missing only permission/prerequisite notes and a fuller picture of the reply contents beyond the wrong-layer warning.

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 only 33%, so the description must compensate — and it does for the critical `layer` parameter, giving meaning (0-3 tile layers, 4 shadow bits, 5 region ids) well beyond the bare integer 0-5 in the schema, plus the omit-to-infer behavior. It leaves tileId/rect/cells coordinate semantics largely to the schema, so it only partly closes the gap.

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 opens with a specific verb+resource: 'Write tile ids on one map', immediately establishing a mutation of map tile data. It is clearly distinguishable in substance from read-oriented siblings like describe_tiles and flag-oriented set_tileset_flags, though it never names an alternative explicitly, keeping it short of a 5.

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 clear usage modes — 'Pass explicit cells, or a rectangle to fill' — and adds a conditional rule ('leave layer out and each tile goes to the layer its own slot belongs to'). What is missing is explicit routing against sibling tools (e.g. when to prefer describe_tiles or batch), so no exclusions are stated.

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