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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered; the description adds genuinely non-obvious behavior — UTC whole-day inclusive date bounds, newest-first ordering, and the fact that a dated first page returns `earlier_matches` from just before the range. It does not explain how the list behaves when brand_id is omitted or how paging interacts with earlier_matches, so not a 5.

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-loads purpose and ordering, then filters, then the routing heuristic — good information ordering with no filler. The final sentence about `earlier_matches` is somewhat convoluted and costs length, but it is conveying a real edge case rather than padding.

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?

No output schema exists, and the description compensates by documenting ordering and the `earlier_matches` shape returned on a dated first page. Still missing: default page size / how limit and offset interact, and the fallback behavior when brand_id is not supplied — meaningful omissions for a 9-parameter list tool.

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?

With 67% schema coverage the schema does part of the work, but the description adds real semantics for the date params (YYYY-MM-DD covers the whole day, UTC, both ends inclusive) and explains the intent behind `kind`. Pagination params (limit, offset), work_id, and user_goal are left entirely to the schema, which is a gap given there are 9 parameters.

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 and resource ('List a brand's images and videos') plus default ordering ('newest first'), which is exactly the kind of scoping an agent needs to distinguish this from sibling lookups like find_creation. The named filters (search, kind, created_after/before) further pin down what the tool returns.

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 routing rule: for 'what did we make this week / last month / since Monday', pass dates here 'rather than reading pages of everything', with a worked example. It lacks an explicit contrast with the obvious sibling alternative find_creation (single-item lookup), so it stops short of a 5.

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