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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's job is to add operational context — and it does: result count is capped at five short snippets, and output is constrained by 'word and reading limits', plus an access restriction to chapters open to the member. Minor gaps remain (ranking/relevance behavior, what an empty result looks like) but this is meaningful added context.

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 short sentences, both front-loaded with the most decision-relevant information: first what it finds and where, then what comes back. No filler or restatement of the name.

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?

With no output schema, the description carries the return-value burden and does so at a high level (up to five short snippets, bounded by word/reading limits) while also disclosing the access constraint. It stops short of describing relevance ordering or empty-result behavior, but an agent has enough to call 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 description coverage is 100%, so all four parameters are already documented, including the enum languages and the 2-80 character query constraint. The description only echoes the keyword nature of the query and the five-result cap; it adds no syntax, matching, or language-resolution detail beyond the schema. Baseline 3 is appropriate.

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 and resource ('Find paragraphs by keywords') and scopes it to 'chapters open to the signed-in member', which separates it from the sibling search_books (which searches across books, not inside one). It never names the alternative explicitly, but the 'in book' framing plus the required id parameter make the distinction inferable.

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?

Usage is implied rather than stated: the description establishes the precondition that only chapters open to the signed-in member are searched, which is real guidance. It gives no explicit when-to-use/when-not guidance and doesn't point to alternatives like get_passage, find_quote_source, or search_books for locating the title id first.

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