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

Annotations already cover readOnly/openWorld/idempotent, yet the description still adds real behavior: 24 results per page, the fact that clips too short for the loop are excluded, and the meaning/size of the returned URLs. It does not mention auth requirements, rate limits, or empty-result 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?

Front-loaded with purpose, then pagination, then usage and parameter clarification. Dense but each sentence carries information; it is a single run-on paragraph that could be broken into clearer units.

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 appropriately carries the return-value burden by describing thumbnail_url, preview_url, and preview_video_url. Combined with pagination and integration guidance, it is nearly complete, though error/empty-result handling is unaddressed.

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, but the description adds genuine meaning: orientation is mapped to aspect ratios ('portrait for 9:16 and 1:1, landscape when 16:9 is among the formats') and seconds is tied to the clip-length filtering rule. q and kind are left to 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?

The description opens with a specific verb and resource: 'Find stock photos or clips to use as a background.' The intended use (background media) is stated, which is clearer than most siblings. It doesn't explicitly contrast itself with upload_background, so it stops short of full sibling differentiation.

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 explains how the result is consumed ('Pass an item's id as look.background.stock_id ... or as a Canvas's stock_id to use it instead of the director's pick') and the Canvas-vs-Look loop distinction via the seconds parameter. It gives clear context but never states when not to use this tool or names an alternative.

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