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

Despite having readOnlyHint, idempotentHint, and destructiveHint annotations, the description adds substantial non-obvious behavior: the corpus records only that passages are connected, never why, so no relationship type should be inferred. It also discloses the 20-vote materialization floor and the result limitation, which materially changes how an agent should reason about minVotes. This goes well beyond what annotations alone provide.

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?

Three sentences carry the main purpose, a critical inferential caveat, and a data-materialization warning with no filler or repetition. The most important information is front-loaded, and every clause earns its place. It is dense but immediately scannable.

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?

For a read-only tool with a full input schema and an output schema, the description covers all the unusual aspects an agent needs to know: ordering, absence of relationship types, minVotes floor behavior, and where to get the full corpus. Nothing important that is not already in the structured metadata is missing.

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?

The input schema already documents all four parameters with 100% coverage, so the baseline is 3. The description adds meaningful semantics beyond the schema: minVotes has a hard materialization floor, osis is scoped to verses or chapters, and results are ordered by crowd support rather than arbitrary relevance. It does not add much detail about offset/limit or output, but the schema already covers those.

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?

The description opens with a specific verb and resource: it returns cross references for a verse or chapter, ordered by crowd support. This makes the tool distinct from sibling tools by pinpointing exactly what is returned, rather than restating the title. The nuance that entries carry no relationship type further sharpens what the tool is and is not able to provide.

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?

The description gives a clear usage context: use this for verse/chapter cross references and explains that lowering minVotes will not produce more results below the materialized floor. It also directs agents wanting the full corpus to the bundled dataset, which is an explicit exclusion. It does not explicitly compare against get_connections or other sibling tools, so a perfect score is not warranted.

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