delete_scene

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

No annotations are provided, so the burden is on the description. It does disclose in plain terms that the operation deletes 'everything in that row,' which is valuable side-effect information for a destructive tool. However, it omits other behavioral aspects such as reversibility (undo support), confirmation flows, or the meaning of 'row' in the UI context, which would be especially valuable given the tool's destructive nature.

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 extremely economical: one front-loaded, information-dense first sentence followed by a clearly formatted parameter line. Every word earns its place, and there is zero fluff or redundancy. The format makes key safety information (cascading delete, 1-based indexing) immediately scannable without restating the schema.

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 single-parameter tool, the description covers the core essential detail of cascade deletion and indexing. However, given its destructive nature and the existence of related tools (fire_scene, delete_track, duplicate_scene), the description would be more complete with a brief safety note (e.g., 'This cannot be undone') or a clarification of the 'row' concept. The presence of an output schema helps, but the description itself remains minimal.

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 provides no description coverage (0%), so the description must carry the parameter-meaning burden. It does so effectively by clarifying that scene_index is the scene number and, importantly, that it is 1-based. This disambiguates the indexing convention, which is a common source of off-by-one errors and is not present in the schema. The description adds clear practical value beyond the schema.

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 uses a specific verb ('Delete') and a clear resource ('scene'), and adds meaningful scope with 'and everything in that row,' which distinguishes it from similar scene-related operations like fire_scene or duplicate_scene. It clearly communicates the cascading delete behavior, which is the most important differentiator. However, it could be slightly more explicit about the irreversible and destructive scope of the row.

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 guidance on when to use this tool versus alternatives. The description does not mention when not to use it, contrast it with create_scene/duplicate_scene/fire_scene, or warn about prerequisites (e.g., stopping playback first). It relies entirely on the name and context for usage decisions. While the destructive nature is implied by 'delete,' no practical guidance is offered.

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