upload_book

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

Annotations already declare write, non-destructive, idempotent, closed-world. The description adds real behavior beyond that: the source files must be local and readable, the bytes are transferred to the server, and the title doubles as the on-disk folder name. It is silent on duplicate handling despite idempotentHint=true, and on permissions or size/timeout limits.

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 action and then a structured Args block, which is the right shape. The middle paragraph is chatty ('Audiobookshelf has no wishlist...') and spends words justifying the tool rather than describing it, though the information is not redundant.

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?

Output schema exists, so return values need not be explained, and all six parameters are documented. What is missing is behavior an agent would want before a large write: what happens on a duplicate upload (idempotentHint claims safety but the description implies plain creation), and whether the call blocks on large transfers.

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 0%, so the description carries the full burden and does: library_id and folder_id are given provenance ('from list_libraries', 'from the library's folders'), title's dual role as item and folder name is stated, files is clarified as absolute local paths that may also include cover/ebook/PDF, and author/series are explained in terms of folder structure.

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+resource ('Upload audio files as a new book, creating the library item') and immediately scopes it against the rest of the server ('This is how a book that is not already on the server gets in'). An agent can distinguish this from create_upload, add_podcast_from_feed and create_items_batch_scan without opening any 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 clear when-to-use context plus an implicit exclusion: no wishlist, no fetch-from-title, files must already exist locally and be readable by this machine. It never names an alternative sibling by name (e.g. add_podcast_from_feed for non-book media), so routing is inferred rather than explicit.

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