apply_autotile

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

With no annotations, the description carries full burden for behavioral disclosure. It reveals key behaviors: computes edge variants from 8-neighbour connectivity, auto-sanitizes shapes to be 4-connected with no diagonal pinches or 1-cell holes, and recomputes the border ring of existing same-autotile cells. It also directs to render_map for preview. This is substantial transparency, though it does not mention error handling or side effects on overlapping layers.

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 compact and front-loaded: it opens with the core action, then lists the four shape modes with guidance, and closes with sanitization and preview notes. Every sentence adds value; there is no filler. The structure uses clear formatting with code-styled parameter names, making it scannable.

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?

Given the tool's complexity (four mutually exclusive shape modes, edge handling) and lack of output schema, the description covers essential operating context: shape use cases, sanitization behavior, border ring recomputation, and preview. It lacks mention of what happens if no shape or multiple shapes are supplied, and does not describe the return value. These are minor gaps for a paint operation, so a 4 is appropriate.

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 description coverage is high (88%), with each shape parameter having a descriptive schema. The description adds value by explaining the relationship between shape modes and use cases, noting that slot 0..6 indexes into tileset autotile_names, and clarifying width recommendation. It does not duplicate schema details but reinforces and extends them.

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 clearly states the tool's action: 'Paint an autotile... and compute the correct edge variant per cell from 8-neighbour connectivity.' It distinguishes itself from sibling tools by emphasizing autotile-specific edge computation and seamless coastlines/paths/cliffs. The purpose is specific and the resource (autotile slot) is clearly identified.

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 provides explicit guidance on when to use each shape mode: 'USE for ponds/lakes/forest patches' for blob, 'only for rectangular floors' for region, and the recommendation 'width >=2' for paths. It clarifies the tool is for autotile-safe painting, implicitly distinguishing it from general tile fill tools. It does not explicitly name alternatives or exclusions, but the shape usage guidance is strong.

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