Cross-source alignment

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

Annotations provide only readOnlyHint=true, so the description carries the behavioral load and does so thoroughly: license_class propagation with an explicit PRESERVE instruction, honest absence semantics (status no_match vs not_synced), the 200-ref truncation cap with a truncation note, the `absent_witnesses` roll-up with reason codes, and the cross-script limitation of the collate fold. These are exactly the behaviors an agent cannot infer from the schema or the readOnly hint.

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?

Purpose is front-loaded and almost every clause carries operational information — sentence-vs-verse semantics, absence statuses, range expansion, collate mode. The main cost is a long semicolon-chained paragraph, and the collate explanation is partly duplicated between the description body and the `collate` schema field, which slightly dilutes the density.

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 must describe the return shape — and it does: witnesses in registry order, per-sentence rows carrying urn/language/license_class/source, the `refs` array for chapter and range queries, `absent_witnesses` with reason codes, and the cell-based diff structure for collate. For a five-parameter, multi-mode tool this is complete enough to invoke correctly without guessing.

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 baseline is 3; the description earns above that by adding normalization rules the schema omits (case/spacing/chapter:verse colons normalize), clarifying that a single `ref` may expand into a `refs` array for chapters and ranges, and noting that range results cap at 200. It also reinforces that `work` is optional with a single registered work and that `collate` changes the shape of the reply rather than just a flag.

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 — cross-source alignment of one citation across every registered witness — with a concrete example (the same NT verse in Greek, Latin, Gothic, Armenian, Slavonic). That is clearly distinct from sibling operations like nabu_search, nabu_show, nabu_parallels, and nabu_concord, which either retrieve, compare, or search rather than render one citation across aligned witnesses.

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 real usage context: `ref` may be a citation in the work's scheme or 'a passage urn to pivot from a search/show hit', which tells the agent how this composes with nabu_search/nabu_show. It also explains that `work` is only needed when several works exist and that `collate: true` switches to a diff rather than a listing. It stops short of explicit when-not-to-use guidance or naming a sibling alternative, so it is clear context without exclusions.

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