unity_bakeControl navigation and lighting bakes: start, wait for completion, or clear existing baked data for scene changes.
Starts, waits for, or clears navigation and lighting bakes. Supported actions: bake_navmesh, bake_lighting, wait_for_bake, clear_navmesh, clear_baked_data. Additional action-specific parameters are passed through unchanged.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag the tool as destructive, and the description adds that it can 'wait for' a bake, suggesting blocking behavior. However, it does not explain what clearing does in detail, whether waits can time out, or any side effects beyond what the annotation already conveys.
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 concise and front-loaded: the first sentence states the core purpose, the second lists valid actions, and the third explains parameter passthrough. Every sentence earns its place and there is no filler.
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 multiple actions, destructive behavior, additionalProperties, and no output schema, the description is too thin. It omits per-action parameters, return behavior, and blocking semantics, leaving a capable agent to guess at important invocation details.
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%, and the description largely repeats the enum values. It mentions that action-specific parameters are passed through unchanged, but it does not enumerate or explain those parameters, so the agent still lacks enough information to construct calls for non-obvious actions.
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 that the tool starts, waits for, or clears navigation and lighting bakes, and it lists the supported actions. This makes the resource and operations identifiable, though it does not explicitly distinguish itself from sibling tools by name.
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 when to use the tool—when performing bake-related operations—but it provides no explicit guidance about when not to use it or which alternatives to prefer. The action list gives some context, but exclusions and alternative routing are absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.