auto_scene_report

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does convey the output contents in detail (what metrics and issues are returned) and implies a read-only analysis by calling it a 'report.' However, it does not explicitly state that the tool makes no scene modifications or clarify any side effects or performance implications. It covers the return value well but stops short of explicit safety/efficacy disclosure.

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 short and front-loaded with the core purpose on the first line, followed by an itemized return list that is easy to scan. Minor redundancy exists: 'compact format' in the first line is restated by 'All in a single compact response' at the end, which could be trimmed without loss.

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 simple zero-parameter tool with no output schema and no annotations, the description gives a solid account of the returned fields, which is the main thing an agent needs to call it. It falls short on contextual completeness because it does not explain how this report differs from several overlapping sibling analysis tools (get_scene_summary, analyze_mesh_quality, get_mesh_statistics), leaving the agent to guess which one is appropriate.

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 and the schema is empty with 100% coverage, so there is nothing for the description to disambiguate on inputs. Per the baseline for zero-parameter tools, the description appropriately adds value by detailing what the caller should expect in the output rather than explaining parameters.

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 the tool performs a full scene analysis and reports quality metrics with a specific verb-target ('auto_scene_report' = analyze scene). It enumerates the exact contents of the report (poly count, material count, lighting, camera, bounding box, non-manifold/ngon issues), which is specific and useful. However, it does not differentiate from close siblings like get_scene_summary, analyze_mesh_quality, or get_mesh_statistics, which likely overlap in scope.

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 guidance on when to use this tool versus its siblings. Several sibling tools (get_scene_summary, analyze_mesh_quality, check_production_readiness, get_mesh_statistics) appear to offer similar reporting/analysis functions, yet the description gives no indication of how the agent should choose among them. No exclusions, prerequisites, or alternative routing are provided.

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