compare_books

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

With zero annotations, the description carries the full burden and delivers: discloses that books are fetched, ranked best-to-worst by average rating, and that derived metrics pct_positive and pct_critical are computed from ratings_histogram, including their semantic purpose (measuring divisiveness). This is exactly the non-obvious behavioral disclosure an agent needs.

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?

Four sentences, opening with the core purpose and progressively adding derived-field semantics and input constraints. Each sentence earns its place, though the middle sentence is somewhat long and could be split for scannability.

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 a rich output schema covering return values and low tool complexity (single param, no enums), the description provides sufficient completeness: ranking behavior, derived fields, and ID-source expectation are all addressed. Missing edge-case behavior (e.g., error on <2 or >10 IDs) is a minor gap.

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 0%, so the description must and does compensate: it states that book_ids should be 2-10 identifiers sourced from search_books and what they're used for. Loses one point for not stating the ID format (e.g., ISBN vs internal ID), though 'from search_books' mitigates ambiguity.

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?

Uses a specific verb ('Compare'), a specific resource ('books'), and a concrete criterion ('by rating and rating distribution'), clearly distinguishing batch comparison from single-item siblings like get_book and get_reviews without naming them.

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 clear context for when to use: 'Pass 2-10 book ids (from search_books etc.)', establishing both the expected input source and cardinality constraint. Stops short of explicit when-not-to-use or named alternative conditions.

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