Random pick

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

Annotations already declare read-only/non-destructive/idempotent, and the description adds genuinely new behavioral context: results are scoped to the Plex Home user so 'unwatched' is per-user, each pick is the same record shape list_media returns, and detail=true enriches the record for explanation. It does not cover edge behavior (e.g. what happens when fewer than count items match), which keeps it at 4.

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 the core identity and the default pick count, then progressively more detail. Dense and largely waste-free, though the mid-sentence 'and so on' and the trailing detail clause make the last sentence slightly sprawling.

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 18 optional params and no output schema, the description does the right work: it describes the returned record shape and what detail adds, which an agent needs for follow-up reasoning. The remaining gap is behavior under sparse results (empty or short result sets) and the count cap, neither of which is mentioned.

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 low at 39% across 18 params, so the description has to compensate. It does add meaning for the important ones — count default of 3, the user-scoping of 'watched', detail's enrichment, and the combinability of genre/decade/maxDurationMin — but leaves rated, studio, country, library, addedSince, collection, contentRating and the lastViewed* params unaddressed. Partial compensation only.

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 ('N random items') plus the key qualifier that it uses the same filters as list_media, and labels itself as the 'just pick something' tool. An agent can immediately distinguish this sampling tool from the exhaustive list_media sibling 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?

It establishes the use case (pick something at random) and points at list_media as the filter reference, plus a concrete recipe: 'Combine watched=unwatched with genre, decade, maxDurationMin etc.' That gives clear context. It stops short of an explicit 'do not use this when you need the full list' exclusion, so it is not a 5.

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