Detect Source Scene Changes

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

The description explicitly states 'Read-only', but the annotations declare readOnlyHint: false. This is a direct contradiction between the description and the structured annotation metadata. Because the description contradicts annotations, it does not provide trustworthy behavioral transparency.

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 tight sentences deliver the core purpose and the most important boundary. Every phrase earns its place, and the key differentiator is front-loaded. No unnecessary detail or repetition.

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 description adequately covers the tool's source-relative scope and its main non-behavior. However, the contradiction with readOnlyHint weakens its reliability, and it does not clarify when to choose this over related sibling tools like detect_scene_edits. Given the output schema exists, return-value detail is not required, but the unresolved metadata conflict leaves the context incomplete.

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 100%, so the parameter schemas already document threshold, media_path, maximum_events, and minimum_interval_seconds. The description adds the FFmpeg scene-score context, which slightly clarifies the domain, but it does not add substantial parameter-level meaning 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 clearly identifies a specific operation: detecting probable visual cuts in a local source file via FFmpeg scene scores. It also distinguishes itself from timeline-affecting tools by stating it does not cut a Premiere timeline. This is strong, actionable purpose clarity.

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 communicates the intended context: operate on source media files, not the active sequence. It also provides an exclusion ('does not cut a Premiere timeline'). It does not name alternative scene-detection siblings such as detect_scene_edits, but the scope guidance is clear enough to route selection.

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