Semantic search

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

Annotations already declare readOnlyHint=true, so the description's addition of needing an index and linking hits to calibre_get_figures provides extra behavioral context. No contradictions. Slightly less than perfect because it doesn't mention potential performance implications or error states.

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 description is very concise, using clear, front-loaded language. Each sentence adds meaningful information without redundancy.

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?

Given the complexity (7 parameters, 3 enums, output schema exists), the description covers the main behavioral aspects: scope, target, mode, and dependency on index. It does not detail the output schema (but that is provided separately) or fully explain topK and library. Still, it is thorough enough for an agent to use correctly.

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 input schema has 0% description coverage, but the description explains scope, target, mode, and the relationship between bookId and scope=book. This adds significant meaning beyond the schema. However, it does not explain topK, library, or the query parameter beyond being required.

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 explicitly states it performs 'meaning-based search over the local index' and distinguishes between scopes (library vs book), targets (text vs figures), and modes (hybrid, vector, keyword). This clearly sets it apart from siblings like calibre_search or calibre_get_book.

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 provides clear guidance on when to use each scope, target, and mode. It specifically says 'target=figures searches figure captions instead of text — use when the user asks for a diagram/chart/schema' and explains mode choices (hybrid, vector, keyword). It also notes the prerequisite that an index must be built by calibre_build_index.

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