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

Beyond the annotations (idempotent, non-destructive, closed-world), the description adds genuinely useful behavior: the save is free, it happens only the first time, the Look stays private to the workspace until the video is made public, and only AI-drawn places/props are carried — never the artist. These are non-obvious visibility and content-scoping details that the annotations do not convey.

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?

It is short and front-loads the verb+resource, but it is written as a single elliptical sentence with missing articles and nested parentheses ("(free) Made the first time (...)", "(the director writes its treatment...)"), which forces re-reading. The information earns its place; the packaging does not.

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 one parameter and full annotation coverage, the definition covers cost, idempotency behavior, visibility, and what content is carried over — everything needed to decide to call it. The remaining gap is that no output schema exists and the description never says a Look id/record is returned, which the follow-up plan/quote step depends on.

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% but the schema text is only "The video id", so the description's qualifier that it must be a *delivered* music video meaningfully narrows which video_id is valid. It stops short of saying what happens with a non-delivered or already-saved video, so it is good rather than complete.

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 opening states a concrete verb and object: saving a delivered music video's direction as a reusable Look. That is distinguishable from the delete/get/list look siblings, though the run-on parentheticals ("(free) Made the first time (the director writes its treatment without the song, the lyrics or the artist)") muddy the read rather than sharpen it.

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?

"A delivered music video's..." implies a precondition (the video must already exist and be delivered), and the closing sentence points at downstream consumers (plan_music_video / quote_music_video look_id). However there is no explicit when-not guidance and no statement of what to do if a Look was already saved for that video, so the agent must infer.

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