compose_scene

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

With no annotations, the description carries the full burden and does so substantively: it discloses that the operation is asynchronous ('Poll the returned workflow ID'), resumable ('Interrupted workflows resume without repeating completed stages'), and reversible ('Result has undo_id'), plus a kinematic limitation (arbitrary horizontal yaw yes, tilted anchors no). It omits auth/permission requirements and what gets destroyed or overwritten on save/place, keeping it short of a 5.

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 definition is front-loaded with the core purpose, then terse per-mode and per-constraint lines — dense but each sentence carries information. Domain jargon ('kit', 'upright anchors') is used without definition, so minor clarity is traded for brevity.

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 an 8-parameter, no-annotation, no-output-schema mutation tool this is fairly complete: modes, coordinate convention, async/polling behavior, resume semantics, and the undo_id return are all covered. Gaps remain on 'prefix', on what the workflow result otherwise contains, and on failure conditions, so it is not exhaustive.

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 0%, so the description must compensate, and it does for most parameters: position ('explicit position is metres in engine axes'), yaw (arbitrary horizontal yaw supported, tilted not), mode (save vs place semantics spelled out), template and asset_ids (referenced in the mode=save/place sentences), and anchor_id ('selected upright anchors supply position/yaw'). The 'prefix' parameter is never explained, which prevents a 5.

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 first sentence gives a specific verb chain ('Build and furnish a small scene, or save/place a reusable layout') and names the resource and scope. It spells out the three internal modes (create/save/place), so an agent understands the tool's remit. It does not, however, distinguish itself from scene siblings like arrange_props or edit_scene, which is the one missing element for a 5.

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?

Mode selection is clarified well: 'create builds a matching kit', 'mode=save records selected instances', 'mode=place duplicates saved instances' — that is real within-tool guidance. But there is no explicit when-to-use-this-vs-alternative guidance against the many sibling scene tools (arrange_props, edit_scene, create_prop_set), so the agent must infer the boundary.

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