detect_scenes

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

With no annotations, the description carries the full burden. It does add useful behavior beyond the name: the results are timestamps in source time (not timeline time) and the threshold direction is explained, but it never states whether the call is read-only or mutates project state, whether it is expensive/long-running, or whether results are cached between calls.

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?

Two short sentences with no filler, and the most decision-relevant fact (threshold sensitivity direction) is placed early. It is efficient rather than bloated, though the terseness contributes to the missing operational context.

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 three-parameter analysis tool with no annotations and no output schema, the description should clarify identifier expectations, whether the operation is read-only, and the shape of the returned timestamps (list? per-shot objects?). It covers the return concept loosely but leaves most operational questions unanswered.

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, yet it only explains one of three parameters (threshold, including its direction of effect and default 0.3). The required 'project' and 'asset_id' parameters get no explanation of expected identifier format or scope.

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 identifies the specific resource and result: shot-change timestamps in a video asset, which pairs with the detect_silence/detect_* siblings and is distinguishable from generic inspection tools. The verb itself is left implicit (it describes the output rather than saying 'detects scene changes'), but an agent can still infer the operation reliably.

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?

Usage is implied only: the presence of a threshold hints at tuning sensitivity, but there is no statement of when to call this versus inspect_media or check_frames, no prerequisites (does the asset need to be imported/analyzed first?), and no when-not guidance.

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