get_actor_bounds

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

Annotations already cover the safety profile (readOnly/idempotent/non-destructive), but the description adds real behavioral context beyond them: editor-world-only scope, that 'all' is inflated by interaction/trigger shapes while 'mesh'/'rendered' excludes them, and the failure signal ('valid=false with a zero extent means no contributing geometry was found'). It stops short of mentioning any cost, caching, or timing caveats, so it is strong but not exhaustive.

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?

Purpose and scope are front-loaded, followed by rationale, the editor/PIE boundary, and the return shape. Dense and slightly over-punctuated with quotes and dashes, but nearly every sentence carries distinct information rather than restating the schema.

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?

There is no output schema, yet the description spells out the full return object (actor_name, components, valid, component_count, origin/extent/min/max) and the meaning of the zero-extent/valid=false case. Combined with the editor-world restriction and filter semantics, an agent has everything needed to call and interpret it.

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 100%, so the baseline is 3. The description contextualizes the `components` filter (why 'all' over-reports and why 'mesh' hugs visible geometry), but the three option values and `include_child_actors` are already fully documented in the schema, so the added meaning is marginal.

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?

States a specific verb and resource ('Measure how BIG an actor really is: its aggregate world-space bounding box') with the exact returned fields, and differentiates itself from nearby tools by naming the alternative (overlap_scene/raycast_scene for PIE worlds) and the fallback (reading a component property). An agent can distinguish it from siblings without opening another 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?

Gives explicit use cases ('size oracle for placement and footprint questions', 'honest test for did that volume/brush actually get built') and names the case it does not cover ('Editor world only -- for a PIE-world footprint use overlap_scene/raycast_scene'). When-to-use, when-not-to-use, and the alternative are all stated.

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