get_scene_bounds

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

Annotations already establish readOnly/idempotent/non-destructive, so the description's job is to add context, and it does: it discloses that only LOADED actors are seen, that an unloaded region contributes nothing, and that the box therefore reads smaller than the map. It also enumerates the return shape, which is useful given there is no output schema. It does not mention performance or cost of a whole-world scan.

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 purpose is front-loaded and the sibling/scope caveats follow in a natural order with no filler. The colon-and-parenthetical opening is slightly dense, but every clause carries information.

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 single-optional-param read tool with no output schema, the description supplies both the scoping caveat and an explicit return-shape listing (valid/origin/extent/min/max/actor_count). An agent has everything needed to call it correctly and interpret the result.

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 baseline is 3; the description earns a point by clarifying the semantic effect of actor_names — that passing it narrows the aggregate to an explicit subset rather than merely filtering results. It adds interpretation of how the parameter changes the computed box.

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?

It states a specific verb+resource (world-space bounding box aggregated over level-bounds actors) and immediately distinguishes itself from the sibling get_actor_bounds. The scope (persistent level plus loaded streamed levels) is explicit, so an agent can tell what it computes without opening the schema.

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?

It names the exact use case ('map extents / where-is-everything questions') and the alternative with its selection condition ('use get_actor_bounds for a single actor'). It also adds a when-not caveat about unloaded World-Partition regions, covering the main misuse risk.

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