Search books

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

The description discloses important behavioral traits beyond the readOnly annotation: it explains that Calibre-Web returns all matches in a single response, that broad queries are truncated client-side, and that totalFound indicates the real count. It also mentions that entries include download URLs and a cover URL, and directs to get_cover for the cover image. This gives the agent a full picture of the tool's behavior and limitations.

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?

Three sentences, each earning its place: the first states purpose, the second explains truncation behavior, the third describes response content and links to a sibling tool. No wasted words, and the most critical information is front-loaded.

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 search tool with two parameters and a readOnly annotation, the description covers purpose, searchable fields, truncation behavior, totalFound, and response content. It does not mention sorting or order, which could be relevant for pagination. However, given the absence of an output schema and the complexity of the tool, the description is nearly complete and provides sufficient context for an agent.

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?

The schema covers 100% of parameters with descriptions, so baseline is 3. The description adds value by specifying which fields the query parameter applies to (title, author, series, publisher, tags), which is not in the schema's 'Search term' description. For the limit parameter, the description adds no additional meaning beyond the schema's min/max/default. Overall, the description provides meaningful context beyond 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?

The description starts with a clear verb+resource: 'Searches the library by title, author, series, publisher and tags.' This specifies exactly what the tool does and which fields it searches, distinguishing it from siblings like list_books (which likely lists all books) and get_cover (which fetches a single cover image).

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 implies usage for searching by various fields, and the context of truncation and totalFound helps set expectations. However, it does not explicitly state when to use this tool versus alternatives like list_books or get_shelf_books, nor does it provide exclusion criteria (e.g., 'Use this for ad-hoc queries; use list_books for browsing all books'). The guidance is clear but not exhaustive.

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