set_tile_flags

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

With no annotations, the description fully discloses mutation behavior: non-destructive merge, autotile-kind application, commit choke point with dry-run/diff, and the return shape. This goes well beyond minimal transparency for a write 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?

The description is information-dense but every sentence earns its place: purpose, merge behavior, key parameter semantics, autotile special case, write path, and return shape. It is front-loaded and efficiently structured.

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 (11 parameters, nested passage object, autotile behavior, and no output schema), the description covers all essential aspects: what the tool does, how it behaves, special autotile handling, and the exact return payload. It is a complete picture for an agent to invoke it correctly.

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 73%, so the description adds value by explaining passage directions, star/damage semantics, terrainTag range, and the applyToAutotileKind behavior. This compensates for undocumented parameters like bush/ladder/counter, though those remain self-explanatory booleans.

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 edits tile passability/terrain/behaviour flags in a tileset's flags[] array, which is a specific verb+resource. It also distinguishes itself as the 'write side of get_tile_flags', differentiating it from the read tool and sibling editing tools.

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 clear context by positioning this as the write counterpart to get_tile_flags, implying when to use it. However, it does not explicitly name alternative tools or state when not to use it, such as set_map_tile for broader tile edits.

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