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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-structured behavior: default ordering is newest-first, the parameter paginates, and each row exposes the 'reference' that the generate tools consume — useful cross-tool context.

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?

Two compact sentences plus a clause; the scope and ordering are front-loaded, the sibling contrast follows, and the archived branch and row-content note are tacked on. No filler sentences.

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?

An output schema exists, so return-value detail is not required, and the description still volunteers the key row field (reference). For a safe, read-only, idempotent list tool the only real shortfall is the undocumented q/kind/limit parameters.

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 0%, so the description must carry parameter meaning. It clarifies only two of the five: the archived flag (which switches the result set) and pagination via 'page through'/cursor. The q search string, kind enum, and limit cap receive no explanation anywhere.

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+scope: 'Page through the account's uploads alone, newest first.' It also explicitly separates the tool from list_media by noting that list_media 'mixes them with generations,' so an agent can distinguish the two without opening either schema.

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?

Explicitly names the alternative (list_media) and the distinguishing condition, and gives a concrete usage branch for the archived parameter ('archived: true lists the archived ones instead'). It stops short of full when/when-not guidance for the remaining filters such as q or kind.

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