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

Annotations say readOnlyHint=false with idempotentHint=true, and the description supplies the reason: generate=true creates GPT moments. That tells the agent the call can write but is safe to repeat. It does not say whether generation is billed, slow, or async, which would have completed the picture.

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 sentences, all functional, and the core action is front-loaded. But the stacked parentheticals '(...) (gpt and already-created)' sit awkwardly mid-sentence and cost the reader a re-read.

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 two-parameter list tool with no output schema, the description covers the input contract, the side-effecting option, and the downstream handoff to clip_video. It does not describe the shape of a returned moment (fields, ordering, empty-result behavior), which is the main remaining gap.

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% and the generate parameter's description ('If true, generate GPT moments when the video has none yet') already duplicates the prose almost exactly. The description's only real addition is the provenance of video_id (imported SendShort videos.id), which the schema gestures at but does not source.

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?

Opens with a specific verb+resource ('List AI moments for an imported video_id') and pins the scope to imported videos, which separates it from list_videos and get_import_status. The trailing parenthetical '(gpt and already-created)' is intended to describe the moment types returned but reads ambiguously.

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 states where video_id comes from (list_videos or get_import_status), when to add generate=true (only when no GPT moments exist yet), and where the returned ids go next ('clip_video.moment_ids'). That is clear conditional guidance, though no explicit when-not-to-use case is given.

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