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

Annotations already establish read-only, non-destructive, closed-world behavior, so the description's job is to add operational context — and it does: results are vote-ranked with a `votes` field, `total` gives the full count, verse text is embedded, and localized editions can degrade to `note: "fallback: english"`. It also discloses the licensing refusal case and the KJV-numbering invariant with specific caveats for Ukrainian, Douay-Rheims, Geneva, Swedish and Serbian editions. Minor gap: pagination/truncation interaction between `total`, `limit` and the ranked list is not spelled out.

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 purpose and the sibling alternative in the first two sentences, then moving to return shape and then locale caveats in descending priority. It is dense but nearly every sentence carries unique operational information; only the edition-numbering aside is arguably longer than the decision it supports.

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-shape burden and discharges it (referenced verses plus text, `votes` per reference, `total` count, fallback note). For a 5-parameter, 3-required tool the only material omission is the accepted format for `book` and how `limit` interacts with the vote ranking.

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% (book, chapter and verse have no descriptions), so the description must compensate, and it substantially does: it pins down that book/chapter/verse are always KJV numbering and explains the `lang` default (conversation language, KJV outside trulyrandomverse.com/ai) and the fallback note. It leaves the `book` string format (e.g. 'John' vs 'JHN') unspecified, which is a real ambiguity given a bare string parameter.

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 ('Get cross-references for a verse') and immediately characterizes the data source (OpenBible.info, vote-ranked, union of links under either verse). It also names the sibling it is not — get_strongs_occurrences — with the distinguishing criterion (thematic/teaching links vs. shared Hebrew/Greek lemma), so an agent can pick between them without opening a 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?

Explicit routing guidance: use get_strongs_occurrences (with `followed_by`) when the link is a shared original-language word, and use this tool for thematic/teaching links. It also gives a when-to-use payoff ('cite scripture-with-scripture without a second lookup') and covers the lang/edition decision path, including what happens when the localized translation is missing.

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