search_books

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

Annotations already declare readOnlyHint and openWorldHint. The description adds valuable behavioral context: 'no auth', the exact return JSON structure (query, searchType, count, books[]), and crucially explains that the returned 'id' is the catalog UUID used as 'book_id' by every other tool. This connects the tool's output to the broader API. No contradictions with annotations.

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 accomplish everything: (1) purpose + return shape, (2) primary use case, (3) sibling differentiation. Every sentence delivers unique, actionable information. No 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?

Given the tool's complexity (3 params, rich schema, no output schema), the description covers the key gaps: return format, the critical linking of 'id' to other tools, and sibling distinction. It does not mention pagination beyond the limit parameter, but the schema already covers that. The 'openWorldHint' annotation handles result variability. Overall, very complete for a search tool.

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 100% – all three parameters have clear descriptions including constraints and defaults. The description does not repeat param details, which is appropriate. It adds mild value by noting the relationship between searchType and query (e.g., ISBN prefix), but this is already implied by the schema. Baseline 3 is correct.

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 opens with 'Search the public SansFiction catalog (no auth)', clearly stating the verb (search), resource (catalog), and scope (public). It uniquely identifies the tool's purpose and distinguishes it from siblings by referencing 'search_my_library' and '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?

Explicitly states the primary use case: 'your entry point for discovery — resolve a title/author/ISBN into a book_id'. It then provides clear when-not-to-use guidance by naming 'search_my_library' for signed-in user shelves and 'get_book' for full details after having an id/slug.

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