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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, but the description adds valuable context beyond those annotations: it discloses the BM25 fallback when the embedding service is down and fully describes the return payload. This is a rich behavioral disclosure for a search tool.

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?

Front-loaded with the purpose, then clearly labeled sections for when to use, when not to use, fallback behavior, and return shape. Despite including a full return schema inline, every sentence earns its place and the structure is highly scannable.

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 that there is no output schema, the description supplies the full return object shape. Annotations cover the safety profile, the input schema covers parameters, and the description covers routing and fallback behavior. Nothing material is missing for an agent to invoke it 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?

Schema coverage is 100%, so the schema already documents query, lang, and limit. The description adds meaning beyond the schema by explaining that the query should be a natural-language paraphrase or theme, with concrete examples, though it does not elaborate on the lang or limit parameters.

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?

States a specific verb+resource ('Semantic passage search over a neural embedding index') and explicitly distinguishes the tool from keyword/BM25 search. It also names sibling alternatives (cyberlibrary_verify_quote, cyberlibrary_get_chunks), so an agent can route correctly without opening other schemas.

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?

Provides explicit 'When to use' criteria with illustrative paraphrase/theme examples and an explicit 'Do not use' list naming the better sibling for exact quotations and whole-book reads. The alternatives are named with their conditions, leaving nothing to inference.

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