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

Annotations already cover the safety profile (readOnlyHint, destructiveHint false, openWorldHint false), yet the description still adds substantial behavioral context: the KJV default edition, that non-redistributable editions are refused outright, and that book/chapter/verse always use KJV numbering so editions with divergent chapter numbering (Ukrainian, Douay-Rheims, Geneva, Swedish, Serbian) may map to a neighbouring verse. It also imposes a hard epistemic rule ("Never write about a translation that was not returned by a tool result this turn"), which is behavioral guidance no annotation could carry.

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 key exclusion, then layered with increasingly specific rules — a sound structure for a tool with this many invocation constraints. It runs long and the "Outside trulyrandomverse.com/ai the default edition is the KJV" framing is deployment-specific clutter, but nearly every sentence carries operational weight.

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 must carry behavior, defaults, refusal modes and numbering caveats, and it does all of that for a 5-parameter tool. The remaining gap is the dangling `lang` reference, which leaves the agent unsure how to actually request a non-English edition; the missing return-shape detail (verse references per edition) is minor.

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 40%, so the description has to compensate, and it largely does: it explains the 2-5 entry constraint on versions, the KJV-numbering contract for book/chapter/verse, and how to reach non-English editions. The major flaw is that it instructs the caller to "pass `lang` for another" edition, but no `lang` parameter exists in the schema — a caller following that instruction will fail, and the actual mechanism (non-English codes inside `versions`) is only revealed by the schema's own array description.

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 ("Compare a verse (or short passage) across multiple Bible translations side-by-side") and explicitly names the sibling it is not: "do NOT call this just to fetch a single version (use get_verse_text for that)." An agent can distinguish this from get_verse_text, keyword_search, and the commentary tools without opening any 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?

Gives concrete user phrasings that select the tool ("how does the ASV/BSB say…", "compare KJV and YLT on…"), an explicit exclusion with a named alternative for single-version fetches, a 2-5 version operating range, and a mandatory batching protocol when more than 5 versions are requested. That is as close to exhaustive when/when-not/alternatives guidance as a description gets.

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