Library changes

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed world), and the description adds non-obvious behavior an agent could not infer: Plex bumps updatedAt during background refreshes so 'updated' may contain no-op entries, limit applies per bucket, and detail=true silently caps limit at 25. That is exactly the kind of caveat that prevents misinterpretation of results.

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?

Every sentence carries distinct information: bucket definitions, the overlap guarantee, the refresh caveat, the date format, the kind enum, the episode tip, the sibling alternative, and the two limit behaviors. It is front-loaded with the core purpose and no sentence is filler.

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?

There is no output schema, so the description must convey return shape, and it does: two named buckets plus the extra fields detail=true adds (directors, actors, collections, summaries). Combined with the annotations and the per-parameter notes, an agent has everything needed to call it correctly and interpret the response.

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 the load, and it does for four of five parameters: since accepts ISO or relative like '-7d', kind enumerates values and defaults to the library's own kind, limit is per-bucket, detail caps limit and adds fields. Only the 'library' parameter's default ('Movies') and limit's max of 200 are left to the schema.

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 combination ('what changed in a library since a cutoff') and immediately defines the two returned buckets ('added' vs 'updated') with the guarantee that they never overlap. This is enough for an agent to distinguish it from siblings like list_media or library_stats without opening a 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?

Gives concrete usage guidance: 'Use episode in a show library to see new episodes' and routes collection lookups to list_media with kind 'collection'. It lacks explicit when-not-to-use guidance versus siblings such as library_stats or watch_history, but the positive routing is clear.

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