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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered and the search description is consistent with it — no contradiction. The description adds useful return-context (work-level records, edition counts, cover IDs, reading availability) and the work-vs-edition distinction, though it does not disclose pagination depth, rate-limit behavior, or failure modes. Given the annotations carry the read-only disclosure, a 3 is appropriate.

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 with zero filler: purpose first, then capability enumeration, then usage routing to the editions sibling. Every sentence earns its place and the structure front-loads the most decision-relevant information.

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 an 11-parameter, fully-schema-documented read-only search tool with an output schema covering the return values, the description is complete: it states purpose, capability set, the query-versus-filter usage pattern, and the sibling to route to for edition detail. Nothing an agent needs to invoke it correctly is missing.

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%, so the schema fully documents all 11 parameters including the language MARC-code behavior, sort semantics, and include_availability latency. The description adds modest value by noting that 'query' can be swapped for compiled field filters ('Use query for general search or combine specific field filters'), helping the agent choose between search strategies, but it otherwise repeats what the schema already states. 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 a specific verb plus resource ('Full-text book search across Open Library works'), then enumerates the supported filter fields (title, author, subject, publisher, ISBN, language) and the return shape (work-level records with edition counts, cover IDs, reading availability). It explicitly differentiates from siblings by stating results are work-level and routing edition-level work to openlibrary_get_editions, so an agent can tell it apart from get_edition/get_editions and the author/inside search tools without opening the schema.

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 gives actionable selection guidance: 'Use query for general search or combine specific field filters' tells the agent which parameter path to choose, and 'Results are work-level — drill into editions via openlibrary_get_editions' names an alternative tool and the condition that selects it. It does not explicitly state when to prefer openlibrary_search_authors or openlibrary_search_inside over this tool, leaving some sibling differentiation to inference.

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