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

Annotations only cover the safety profile (readOnly, non-destructive, closed-world), and the description adds substantial behavior beyond them: excerpts are marked and capped at ~4,000 characters, duplicate texts of the same writer collapse into also_under, oversized ranges return mode: range_too_large at >200K chars, and results are interleaved by writer and century so limit does not starve variety. The writer_note caveat about Philo, Josephus, and cross-reference entries is a valuable authenticity warning no annotation conveys.

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?

Dense but front-loaded: identification first, then return shape, then the verse/verse_end mechanics, then limit behavior, then the failure mode and steering guidance. Every sentence carries operational information — there is no filler or restatement of the title.

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?

There is no output schema, so the description carries the return contract itself and does so thoroughly: father name, year AD, verbatim text, excerpt/also_under markers, total, quotes_by_verse, and the range_too_large mode. Combined with its coverage of the range-sweep parameter interaction, an agent has everything needed to call and interpret this tool 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 only 40% (limit and verse_end documented, book/chapter/verse bare), but the description compensates well: it explains that verse alone targets a single verse while verse_end must be passed ALSO to sweep a range, and it describes how limit interacts with round-robin selection and total/quotes_by_verse. The book/chapter/verse parameters remain self-evident rather than explained, keeping this below a 5.

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?

Opens with a specific verb and resource — 'Fetch quotes from the early church fathers ... on a verse or verse range' — and names the representative writers. It also positions itself against the sibling search_fathers by explaining that search_fathers with a quote_id returns the full text, so an agent can separate the two without inspecting 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?

Explicit invocation rule at the end ('Call it when the question concerns a passage's meaning, theology, or historical interpretation'), plus concrete exclusions and escalation paths: use verse alone vs. verse_end for a sweep, fall back to search_fathers for a full quote, and on range_too_large 'ASK THE USER which passage to focus on rather than calling repeatedly.' It even warns against declaring a verse empty before checking quotes_by_verse.

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