inspect_3d_scene

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

Annotations declare readOnlyHint=true and destructiveHint=false, which the description aligns with. It adds valuable behavioral details beyond annotations: it times out if no renderer responds, detects old widgets via renderer_matches_bundle, and compares rendered_revision with the submitted revision. These are not captured in annotations, enhancing transparency. No contradiction.

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 moderately long but densely informative. It front-loads the core purpose ('Inspect loaded geometry and build IDs'), then enumerates the data it reads, and ends with behavioral notes (timeout, revision comparison). Every sentence contributes to understanding the tool, though it could be slightly more compact. It is well-structured and readable.

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?

The tool is complex and reads many scene properties, but it has an output schema that likely details return structure. The description covers the main input (scene_id), behavior (timeout, fallback, revision comparison), and the range of data inspected, which is sufficient for an agent to invoke it correctly. It doesn't explain error cases or the meaning of summary vs full, but the output schema and enumeration reduce the gap.

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 schema has only two parameters, but the description provides no explanation of their semantics. It doesn't clarify what 'detail' levels (summary vs full) imply or what 'scene_id' refers to beyond a scene identifier. With schema description coverage at 0%, the description should compensate, but it doesn't, leaving the agent to infer parameter roles. The only hint is the reference to the active viewer/browser fallback, which is vague.

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 verb 'inspect' and the resource (loaded geometry and build IDs). It enumerates specific properties it reads (coordinates, camera, transforms, etc.), which distinguishes it from sibling tools like list_3d_scenes or capture_3d_view. The mention of 'renderer_matches_bundle' further clarifies a unique behavior, making the purpose unambiguous.

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?

The description gives clear context: it's for reading scene state (geometry, camera, viewport, etc.) from the active inline viewer or browser fallback. It notes timeout behavior and revision comparison as caveats. However, it does not explicitly state when NOT to use it or name alternative tools, so it lacks explicit exclusionary guidance.

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