Squish a video into a timestamped visual + audio activity map

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

The description discloses important behavioral traits beyond annotations: timecodes are ABSOLUTE, the audio band is globally normalized and energy-only, the on-device execution, the ffmpeg dependency, and the drill-down zooming behavior. The idempotentHint is consistent with the repeated-call workflow described.

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 long but information-dense, with every sentence adding a distinct, useful fact. It front-loads the core deliverable and then progressively covers usage, limitations, parameter strategy, and prerequisites, without 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?

For a tool with no output schema, the description compensates by specifying the return shape ('audio.samples[]' with absolute time and normalized level), the output file nature, the visualization workflow, and the environmental requirement. An agent has enough to invoke it correctly and use its results.

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 coverage is already 100%, so the baseline is 3, but the description adds strategic meaning beyond the schema: 3x3 recovers what happened while 4x4–6x6 recovers how it was done, and zoom calls with start/end produce finer timecodes for repeated drill-down. This helps an agent choose parameter values, not just recognize types.

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 names a specific transformation (video → timestamped contact-sheet JPEGs with an audio activity band) and identifies the vision-model use case. Though there are no sibling tools, it clearly positions itself against the manual ffmpeg pipeline, so there is no ambiguity about what it replaces.

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 explicitly states when to use it: for videos too long to ingest, for time-anchored questions, and whenever timestamps are needed. It also tells the agent when not to rely on it for audio semantics ('does not transcribe, classify, or identify sounds') and directs repeated zooming from overview → range → moment.

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