Detect Motion Peaks

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

The description clearly states the operation is read-only and that candidates are only 'probable high-motion moments'; it even discloses the limitation that camera movement, flashes, cuts, and subject motion are not semantically distinguished. Although the annotations mark destructiveHint=false, they do not mark readOnlyHint=true, so the description itself does useful extra work in clarifying safety. It could add more behavioral detail about the return shape (e.g., timestamps and scores), but with an output schema present this is a minor omission.

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 a single compact sentence that front-loads the resource ('bounded local video sample from decoded frame differences'), states the output type ('probable high-motion moments'), and adds an important limitation. There is no filler or redundancy.

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 read-only detection tool with a rich schema (six parameters, all described, with defaults) and an output schema, the description covers the main behavior and limitations. Remaining gaps are minor: it does not explicitly explain how returned peaks should be consumed in an editorial workflow and does not explicitly exclude scene changes as semantic detections, but the limitation sentence largely covers that.

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 schema description coverage is 100%, so each of the six parameters already has a meaningful description with defaults and ranges. The description adds no additional parameter-level behavior beyond calling them the basis for finding motion peaks. Baseline 3 applies because the schema already carries the parameter semantics.

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 verb ('Find') and a specific resource ('bounded local video sample from decoded frame differences'), saying this produces high-motion candidate moments. It explains that it is read-only and editorial candidates, but it does not name a sibling tool that offers a similar alternative. Thus it is specific but not explicitly differentiated from, for example, detect_source_scene_changes or detect_scene_edits.

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 implies usage as a read-only motion-analysis pass over a local video file, and the phrase 'editorial candidates' suggests it is for finding possible moments of interest rather than semantic classification. However, it never explicitly says when to choose it over related tools such as detect_scene_edits, detect_silence, or detect_source_scene_changes, and it omits context (e.g., shall be used for rough-cut selection; for shot changes use another tool). This is adequate but not strong guidance.

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