Expand an existing scene by adding new regions around its borders, preserving the original layers and landmarks for consistent pixel art.
Extend an existing deterministic scene around its borders while preserving the original layers and landmarks.
| Name | Required | Description | Default |
|---|---|---|---|
| top | No | ||
| left | No | ||
| seed | No | ||
| right | No | ||
| bottom | No | ||
| preview_filename | No | ||
| input_map_filename | Yes | ||
| output_map_filename | Yes |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are provided, the description carries the behavioral burden. It does add meaningful traits: the operation is deterministic and preserves original layers/landmarks. However, it does not disclose side effects, whether the input file is mutated or only read, how the seed affects generation, or failure modes. The schema hints at file inputs/outputs, but the description itself leaves those behaviors implicit.
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 a single, efficiently structured sentence with no wasted words. It front-loads the core operation and adds a relevant preservation clause. It is appropriately sized for the tool, though brevity unavoidably sacrifices some parameter-level clarity.
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 tool with eight parameters, no annotations, and no output schema, this description is too thin. It does not explain how to specify extension amounts, what seed does, whether preview_filename is required, what the output file contains, or what happens if the input is not a deterministic scene. An agent could call the tool but would struggle to choose correct parameter values confidently.
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 0%, so the description must compensate for eight parameters. 'Around its borders' loosely explains top/left/right/bottom, and 'deterministic scene' hints at seed, but units, semantics of the integer border values, the meaning of preview_filename, and the relationship between input and output filenames are not explained. The descriptive burden is not met for a low-coverage schema.
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 a specific verb ('Extend'), a resource ('existing deterministic scene'), and a precise scope ('around its borders'). It also communicates key non-destructive traits ('preserving the original layers and landmarks'), which differentiates it from generation, composition, or effect-stack siblings.
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 phrase 'existing deterministic scene' implies a precondition and suggests this is not for creating new scenes from scratch, but there is no explicit when-to-use guidance and no mention of alternatives such as generate_world_map or compose_asset_scene. The tool is left to infer routing from the sibling list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.