add_to_watchlist

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

Annotations already convey readOnlyHint=false and destructiveHint=false, so the mutation is expected; the description usefully adds that the operation is gated behind PLEX_ENABLE_MUTATIVE_OPS=true, which is a beyond-schema operational constraint. It does not disclose what happens when the flag is off, whether the operation is idempotent for items already on the watchlist, or any side effects, so it contains only modest enrichment on top of the annotations.

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?

The whole definition is a single sentence that is action-first and does not waste a word: verb + resource + destination + the one enabling requirement in a parenthetical. Every element carries meaning, with no paraphrase of the schema available.

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?

For a one-parameter tool with no output schema, the description covers what the operation does, where it writes, and the necessary environment gate, which is enough to select and invoke it. The remaining gaps — what happens if PLEX_ENABLE_MUTATIVE_OPS is false or if the item is already in the watchlist — are minor for a simple, non-destructive mutation with a fully documented schema.

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 100%, and the schema already explains ratingKey as a 'local Plex rating key for a matched movie or show' with a clear description. The tool description echo (the 'local' term) matches the schema but doesn't add new meaning, such as how to obtain the ratingKey or what 'matched' means, so the baseline 3 is appropriate.

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?

The description names a specific verb ('Add'), a specific resource ('a local Plex movie or show'), and a specific target ('the account watchlist'), so an agent knows immediately what the tool does. The 'local' qualifier and the watchlist target distinguish it from siblings such as remove_from_watchlist, get_watchlist, and add_to_playlist without needing to open other schemas.

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?

The description states an explicit precondition ('requires PLEX_ENABLE_MUTATIVE_OPS=true'), which is a reasonable gateway for deciding whether invocation is even possible. It does not, however, name the alternatives for the same intent (e.g., get_watchlist to read, remove_from_watchlist to undo, trakt_sync_to_trakt for the Trakt watchlist) or give any when-not-to-use guidance.

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