Media Perceive

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

Annotations establish a non-read-only, open-world, non-idempotent call to an external provider, and the description meaningfully extends this: dry runs make no provider calls, submission needs an exact grant and a configured account, and sampled frames leave visual gaps (a real accuracy caveat). That is substantive disclosure beyond structured fields, though it omits cost/rate-limit behavior.

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?

Three tight sentences with the core purpose front-loaded and operational facts following. Every clause carries information; no padding or restatement of the title.

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?

An output schema exists, so return values need not be explained, and the description covers the dry-run/submit gating, the account/grant prerequisites, and the sampling limitation. The remaining gap is sibling disambiguation, which keeps it from a 5.

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 100%, so every field including the nested limits object is already documented, making 3 the baseline. The description adds only tangential mapping detail ('model intervals map back to source seconds') and the sampling-gap caveat rather than clarifying specific parameters like fps, window_seconds, or authorize_submission.

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?

States a specific verb ('infer') and resource ('separate spoken and visible source evidence') with a clear scope ('across bounded AV windows'), which distinguishes it from pure-audio (audio_transcribe) or pure-vision siblings. However, it never names an alternative in the sibling list, so the agent must infer the boundary itself.

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 a two-phase workflow (dry plan first, then submission) and states the precondition for submission ('exact workflow grant and configured account'). That is useful operational context, but it gives no explicit when-to-use vs video_analyze, audio_transcribe, or video_analyze_windows, leaving the choice to inference.

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