Search books

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: price and free_only filter already-scanned results (implying pages can come back smaller than expected) and narrow ranges may require paging via next_cursor. It stops short of describing result ordering semantics or what a result record contains.

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?

Two tight sentences, front-loaded with what is searchable and then the paging caveat; no filler. Minor deduction for the ambiguous 'rating' term in the attribute list, which reads like a filter but has no matching parameter.

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 9-parameter tool with no output schema and only 56% schema coverage, the description covers the main filters and the pagination caveat but omits sort behavior beyond the enum names and never clarifies what is returned per result (price, discount, rating). Adequate but with real gaps an agent would hit on first use.

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 56%, mid-range, so the description should compensate for gaps and only partly does. It references the query, price bounds, discount, format, and free_only filters and explains the cursor interaction, but leaves sort and subscription_only unexplained and mentions 'rating' even though no rating parameter exists, which may confuse the agent about whether rating is filterable or merely returned.

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 names a specific verb and resource ('Search ebooks and audiobooks') and the primary access axes (title, author, topic) plus the refinable attributes (price, discount, format). It is clear what the tool does, but it never distinguishes itself from siblings like tg_free_books, tg_bestsellers, or tg_browse, leaving overlap for the agent to resolve.

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?

There is usable behavioral guidance about filtering and paging ('price limits and free_only filter scanned results; a narrow range may need next_cursor'), which tells the agent what to expect when narrowing. However, there is no explicit when-to-use versus alternatives and no statement of when this tool is the wrong choice relative to the free-book or bestseller siblings.

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