Repair wrong metadata

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

Annotations declare destructiveHint=true, and the description goes well past that: it names what is replaced (all metadata, hand edits included), that there is no undo on Jellyfin, that locked fields are never overwritten, and that the Jellyfin repair holds the request open so it must not be retried. That is exactly the operational context the boolean hint cannot convey.

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?

Dense and front-loaded: purpose first, then the exclusion, then the destructive warning, then edge-case recovery. It is packed close to the limit of readability and ends with a docs pointer, but every sentence carries distinct information and none 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?

An output schema exists, so return values need not be explained, and the description instead supplies the parts the schema cannot: preview classification of `numbering` versus `title` findings, how films are judged, the no-retry constraint, and the rename-then-rescan fallback. Nothing an agent needs to call this safely and correctly is missing.

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 coverage is 100%, so the baseline is 3, but the description adds resolution logic the schema only partly carries: title goes in `query`, or the id that get_metadata_issues printed, and books are addressed as `grimmory:<book id>` matched by ISBN or title-and-author. It does not elaborate on `user`, `dry_run`, or `confirm` beyond what the schema already documents, so it is not fully additive.

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 ("Repairs films and series whose Jellyfin or Plex metadata does not describe the file on disk") and makes the failure mode concrete with the `Episode 101` shown as S1E1 example. It explicitly separates itself from `trigger_scan` and points at `get_metadata_issues` for id sourcing, so an agent can route correctly without opening another 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 the when (metadata doesn't match the file), the when-not ("Not trigger_scan, which never replaces a wrong title"), the sequencing ("Previews first; confirm to apply"), and a conditional alternative path (use trigger_scan `action: "rename"` on the Sonarr series plus a rescan when a refresh cannot move episodes). It also covers the book case with the `grimmory:<book id>` form.

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