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

Beyond readOnlyHint, the description adds genuinely useful behavior: the tool is free to call, results are ordered newest first, and rows expire (7 days for video and other rows, 12 for files), which materially affects whether an agent can rely on old generationIds. The expiry sentence is compact to the point of ambiguity ('files 12'), and pagination behavior past the 50-row cap is not disclosed.

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 scope statement followed by explicit Args and Returns blocks, with no filler despite covering cost, ordering, expiry, parameters and response shape. Minor redundancy in restating the kind enum already present in the schema.

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?

Because no output schema exists, the description correctly supplies the return shape ({ok, generations:[...]}) and the fields an agent needs to chain into library_get or library_share. The remaining gap is paging: with a 50-row cap and expiring rows, the definition never says how to reach older results.

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 0% schema description coverage, the description carries the full burden and mostly meets it: it names the kind enum values and specifies the limit range (1-50) and default (20), neither of which the schema declares. Only the semantics of 'limit' beyond a count cap, and how to page past it, are left implicit.

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 and scope: the user's generations in the WEB Library at viralmint.net, covering videos, images, voice and music, ordered newest first. It also explicitly disambiguates from a plausible confusion (local files / the desktop app's server), so an agent can tell what this returns without opening the 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?

Provides a clear when-not: this is NOT for files on the local computer, which belong to the desktop app's server. That exclusion prevents the most likely misuse. It does not point to sibling tools for follow-up operations (library_get, library_delete), but guidance for selecting this tool is explicit.

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