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

Annotations already mark the tool as read-only, non-destructive, and idempotent. The description adds useful behavioral detail: it is non-invasive ('without touching it') and returns actual frame samples to let the human/agent see content. No contradictions with 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 fairly long and includes rhetorical emphasis ('WATCH', 'Look at those frames'), but each sentence earns its place by explaining what is returned, how to use it, and why missing it causes guesswork. Slightly over-explains the motivation, but the structure remains sensible.

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 one parameter, high schema coverage, no output schema, and a list of outputs explicitly stated, the description fully equips an agent to call the tool correctly and use the results in the larger scoring/music workflow. No critical information is missing.

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 only parameter, video_url, is fully covered by the schema description ('link to video'), so the description adds little parameter-specific meaning. It clarifies that the video is a URL, but not much beyond the schema. This meets the baseline 3 for high schema coverage.

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 states the action ('WATCH a video and measure it') and enumerates what it returns: exact length, frame rate, resolution, audio presence, shot list with cut times, and a labelled frame per shot. It distinguishes itself from score_my_video and find_soundtrack by explaining its specific role in the scoring workflow.

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 gives explicit when-to-use guidance: use it before find_soundtrack when music is needed but length is unknown, and tells the agent to use a found timecode as a section boundary for score_my_video. It also warns against guessing timecodes, which clearly communicates why this tool is the right choice.

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