Paint map tiles

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

With no annotations, the description carries the load and does so well: it discloses that autotile edge/corner/wall shapes are computed automatically and that neighbouring tiles get re-shaped, that tile id 0 erases, and that operations apply in order. It does not say whether edits are persisted immediately or only staged in a changeset (begin_changeset / commit_changeset are siblings), which is the main remaining behavioral gap for a mutation tool.

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 core action, then organized by operations, tile encoding, layers, and workflow. Dense but every clause carries information; only the example workflow sentence could be trimmed without loss.

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 nested, multi-shape mutation tool with no output schema, the description covers operation semantics, tile formats, layer conventions and a starter recipe. It omits the return value / result reporting and the persistence model, both relevant to an agent calling a write tool.

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?

Top-level schema coverage is effectively 0% (mapId and operations are undocumented), so the description has to compensate and largely does: it enumerates the three operation types (cells/rect/fill), the three tile encodings with their sheet families, the meaning of 0, and the layer map 0-1/2-3/4/5. It adds real value beyond the nested schema, though mapId itself is never explained.

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?

Opens with a specific verb+resource ("Paint tiles onto a map") and immediately scopes it to an ordered list of operations, which distinguishes it from generic map mutators like update_map and from read-only siblings like get_tileset_info and render_map.

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?

Explicitly routes the agent to get_tileset_info / get_tileset_image for tile selection and render_map for verification, and gives a concrete typical workflow (fill layer 0 with an A2 ground kind, then place water/walls/objects). It stops short of stating when NOT to use this (e.g., vs. update_map for non-tile edits).

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