apply_scene_patch

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

The description reveals that the operation is 'transactionally' applied, indicating atomicity and rollback behavior, which is valuable. With no annotations, the description carries full burden for behavioral disclosure. However, it does not mention other traits like permissions, rate limits, or whether the patch is incremental or replaces existing data.

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, clear sentence that is front-loaded with the key action and method. It is appropriately concise, though it could benefit from additional context without becoming verbose.

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?

Given the complexity of the patch schema (many nested objects) and the existence of an output schema (as per context), the description minimally covers the tool's purpose and transactional nature. However, it lacks details on error conditions, default behaviors, or valid value ranges for the patch, leaving gaps for a complex tool.

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%, meaning no parameter descriptions in the input schema. The top-level parameters (scene_name, patch) are not explained in the description. While the nested schema has many internal descriptions, the description adds no semantic meaning for how to form the patch object or what scene_name expects. The agent must rely solely on schema structure.

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 states 'apply a recursive merge patch to a scene' with a specific verb ('apply') and resource ('scene'). It hints at the technique (recursive merge patch) which distinguishes it from full updates. However, it does not explicitly differentiate from sibling tools like update_object or add_object, which might also modify the scene in other ways.

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?

No guidance on when to use this tool vs alternatives (e.g., update_*, add_*, remove_item). The description does not specify prerequisites, restrictions, or scenarios where the tool is appropriate or inappropriate. An agent would have to infer usage from the name and schema alone.

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