list_collision_objects

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

No annotations are provided, so the description carries the behavioral burden. It communicates that the tool reflects current scene state and that indices are meaningful to remove_collision_object, but it does not explicitly state read-only behavior, return shape, ordering, or empty-scene behavior. Adequate but incomplete.

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 short sentence with no filler; the current-scene scope is front-loaded and the index relationship is meaningful. The phrasing is slightly compressed but every clause earns its place.

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 zero-parameter, no-output-schema list tool, the description covers what is returned and why the returned index matters. It does not detail the exact return structure, but the simple nature of the tool makes the description minimally sufficient for correct invocation.

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?

The tool has zero parameters, so the schema imposes no burden. The description adds the relevant index semantics for the companion removal tool, which is the most useful contextual information an agent needs here. Baseline 4 applies.

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 identifies the resource (rods and boxes), the scope (currently in the scene), and ties the result to remove_collision_object's expected index. It is not a tautology and is distinguishable from collision-object add/remove/import siblings, though it lacks an explicit verb.

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?

There is no explicit when-to-use statement or mention of alternatives, but the phrase 'with the index remove_collision_object takes' implies the tool should be called before removal to get valid indices. This is contextual guidance, not clear routing between siblings.

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