get_scenes

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

Annotations already mark the tool read-only and idempotent, and the description adds the important prerequiste that transcript scene detection must be enabled and is disabled only when index_video was called with scene_detection=False. It also hints at typical scene lengths relative to segment_video's limit. This provides useful behavioral context beyond the structured annotations.

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 compact and front-loaded: the core action appears in the first sentence, followed by a clear bulleted list of downstream uses and a one-line prerequiste. Every sentence contributes.

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 read-only retrieval tool with an output schema, the description covers purpose, downstream integration, and the indexing requirement. It is missing only brief parameter semantics for max_results and rationale, which prevents a 5.

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 description coverage is 0%, so the description must compensate, but it only implicitly covers video_id. Neither max_results nor rationale is explained, and the default of 200 or its effect on returned scenes is left to inference.

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 opens with a specific verb and resource: 'Get detected scene boundaries with start/end timestamps.' This clearly distinguishes the tool from siblings like get_transcript or segment_video, and it is not a restatement of the tool name.

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?

It explicitly says to use this first to understand video structure, then pass scene timestamps to ask_video and segment_video, including a note about segment_video's 15s max range. It also states the indexing prerequiste and the only case where scene detection is skipped. It stops short of naming alternative scene sources or explicit when-not conditions, so a 4 rather than 5.

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