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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive, closed-world), so the bar is lower. The description adds genuine behavioral context beyond them: which fields carry the background plates versus thumbnails, that previews are 480 px wide copies, and that previews are null when no photo or video background exists.

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 a short purpose sentence, then a second sentence carrying the field semantics. The second sentence is dense and reads a bit fragmentary due to the dotted field paths, but every clause conveys useful information.

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 must carry the return-shape burden, and it only documents the backgrounds sub-object. The design field and other top-level fields of a Look are never described, so the agent is partially informed about what comes back.

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 description coverage is 100% with a single documented parameter (look_id), so the schema does the heavy lifting. The description adds nothing about the id's format or source. Baseline 3 applies.

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+resource: retrieving a single Look with its design and preview images. The word 'One' implicitly contrasts with the sibling listing tools (list_looks, show_looks), though it never names them. Clear purpose without explicit 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?

No statement of when to use this versus list_looks, show_looks, or get_video, and no prerequisites or lookup context. The singular 'One Look' implies a single-record fetch, but the agent is left to infer that this is the by-id retrieval path.

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