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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false). The description adds genuine context beyond them — 'Read-shared for everyone' discloses access scope — but does not mention pagination, ordering, or return shape.

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 sentence, front-loaded with the resource definition and ending with the workflow. The illustrative examples (golden-hour, neon-night, noir-bw) earn their place by making 'cohesive look' concrete, though the sentence carries several distinct ideas.

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 zero-param list tool with annotations covering safety, the description covers what a pack is and how to proceed after listing. With no output schema, it could say more about what is returned per pack (id/name), but the conceptual content of a pack is conveyed.

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?

The tool takes zero parameters, so the baseline is 4. Nothing in the schema needs compensating for; the mentions of pack and referenceIds describe other tools' inputs, not this one's.

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 resource — 'curated moodboards usable as generation references' — and defines what a pack actually is ('a cohesive look: lighting/grade/mood') with concrete examples. It clearly differentiates from siblings by naming the downstream tools (search_references, referenceIds) rather than leaving the agent to guess.

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?

Gives an explicit workflow: pick a pack for the user's intent, search inside it via search_references(pack), then pin chosen refs via referenceIds. It does not explicitly contrast against sibling get_pack, so the 'when to use this vs the other pack tool' boundary is left partly to inference.

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