refine_with_local_llm

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

No annotations are provided, so the description carries the full burden. It discloses the core behavior (sending to Ollama for expansion) but omits details like requirements (Ollama must be running), error handling, or whether the operation is idempotent. The description adds context about Marble-optimization but lacks deeper transparency.

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?

Two sentences with no waste: first states the purpose, second elaborates on the action and output. Front-loaded and efficient.

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 an output schema, so return values are covered. The description is sufficient for a simple refinement tool, but it could note prerequisites (e.g., Ollama running locally). Given sibling tools, its role is clear.

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 100%, so the description need not add param info; baseline is 3. The description does not provide additional meaning beyond the schema—'short prompt' is already in the prompt parameter description.

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 verb ('Refine'), the resource ('a world prompt'), and the method ('using a local Ollama model'). It also specifies the output is a 'Marble-optimised 3D world generation prompt', distinguishing it from sibling tools that generate worlds directly.

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 implies usage for refining a prompt before world generation, but it does not explicitly state when to use this tool versus alternatives (e.g., generate_world_from_text). No when-not-to-use or alternative guidance is provided.

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