search_books

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses genuinely useful traits: the accepted query language, the empty-string-matches-everything edge case, and the limit bounds (1-200). It does not explicitly assert read-only safety, but 'Search' makes that evident.

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 one-line summary followed by a compact Args block. No filler sentences; every element carries information and the examples are illustrative without bloat. Clean and scannable, though the docstring format is a conventional choice rather than exceptional craft.

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 2-parameter tool with an output schema present, the description covers query syntax, the empty-string edge case, and result limits — while the output schema handles return-value expectations. The only omissions are minor (behavior on malformed queries, result ordering), which do not undermine correct invocation.

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 compensate — and it does so thoroughly. Each parameter gains real meaning: query is explained with three calibre expressions plus empty-string behavior, and limit is given a range and default beyond the schema's bare type and default. This exceeds the compensation baseline for low coverage.

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 ('Search'), resource ('the library'), and distinctive mechanism ('calibre's query language'). The library-level scope implicitly differentiates it from sibling search_in_book, and the query-language detail adds precision. However, it does not explicitly name sibling tools or draw the contrast, so it just misses the top score.

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 how-to guidance — three worked query examples and the note that an empty string matches everything — which implies when the tool applies. But it never states when to prefer this over list_books or search_in_book, and offers no exclusions or conditions. Usage is implied rather than explicit.

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