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

Beyond the annotations it discloses the editing behavior (pauses and false starts removed, long sets cut to 20–60 seconds, captions follow speech), the credit cost of one video, and that the result is asynchronous and must be polled via get_video. None of this is recoverable from readOnlyHint/openWorldHint 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?

A single dense paragraph that front-loads the outcome, then inputs, then cost and follow-up. Every clause carries operational information; nothing is restated from 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?

With no output schema, the description still tells the agent what it gets back and how to retrieve it, plus the credit cost and input sourcing. For a 3-parameter generative tool this covers everything needed to invoke it 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 coverage is 100%, so the baseline is 3; the description adds real value by stating the either/or exclusivity between mediaIds and shootId and by naming where the ids originate (import_media, list_media, start_phone_shoot). It does not explain the optional topic parameter, which is documented only in the schema.

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?

Names a specific transformation: cutting the person's own videos into one vertical video, with speech as the voice track. The word 'own' plus the mention of mediaIds sourced from import_media/list_media cleanly separates it from the sibling make_video.

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?

Explicitly states the two input paths (mediaIds for 1–6 imported videos, shootId for a phone shoot) and routes the agent to get_video for polling. It does not state when to prefer make_video instead, which is the only remaining gap.

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