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

The annotations already establish that this is a read-only, non-destructive, closed-world operation. The description adds useful behavioral detail beyond that: it scans every frame, returns active and idle source-time stretches, includes a padded keep list, and explicitly notes that measurements are relative to the footage and do not identify the activity. It does not discuss performance cost or the non-idempotent hint, but it is substantially more informative than the annotations alone.

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 two tight sentences, front-loaded with the measurement behavior and followed by an important limitation. There is no repetition or filler, and the key scope note about relative measurements is placed clearly.

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 an eight-parameter tool with 13% schema coverage and no output schema, the description leaves most call parameters unexplained and does not describe the structure of the padded keep list beyond naming it. It communicates the core concept and limitation, but an agent still lacks the information needed to set sensitivity, minimum active/idle durations, or padding correctly.

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 only 13%, with just project_id documented, so the description needs to compensate for seven undocumented parameters. It does not explain start, end, min_active_s, min_idle_s, sensitivity, pad_before_s, or pad_after_s; the only vague link is the phrase 'padded keep list,' which hints at padding parameters without defining them. This is a significant semantic gap.

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 states a specific operation: measuring picture motion and sharp sound transients across every frame of the main video, then returning active/idle source-time stretches and a padded keep list. That is clear and concrete. It stops short of explicitly distinguishing itself from likely siblings such as find_silences or find_visual_moments, so it is not a 5.

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 when-to-use guidance, no mention of alternatives, and no prerequisites or exclusions. The agent can infer that this is a finder for motion/sound activity, but nothing tells it when to choose this over other find_* tools or how to scope the search.

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