manage_terrain

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

With no annotations, the description carries the full burden of behavioral disclosure. It does include some detail (e.g., resolution is always 4 in Roblox, smooth uses blend strength), but it fails to mention whether actions are destructive/reversible, require permissions, or what read operations return. This is a significant gap for a mutation-capable 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 structure is logical: purpose, action list, region format, material list. It front-loads 'Edit Terrain' and uses compact bullets/lists. While long, the content is dense and each section serves a purpose given the tool's many actions and materials.

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?

The tool has 27 parameters and 16 actions, but the description omits important context: no output format for read actions, no error/edge-case behavior, and no distinction between read-only and mutating actions. With no output schema or annotations, this leaves significant gaps for an agent to safely invoke the 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?

The description adds value by explaining action-specific parameter relationships, such as clear_region accepting either center+size or a region object, and replace_material using fromMaterial→material. These mappings go beyond the raw schema and help the agent select the right parameters for each action.

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 'Edit Terrain' and then enumerates all supported actions, which clearly establishes the tool's scope as terrain manipulation. However, it doesn't explicitly distinguish this from sibling tools that might also access terrain data (e.g., query_instances), and the long action list may obscure the core purpose.

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 guidance on when to use this tool versus alternatives. The description lists actions but doesn't explain which scenarios call for each action or when to prefer a sibling tool for related operations.

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