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

Annotations cover safety (readOnlyHint) and scope (openWorldHint=false), and the description adds behavioral context they don't: matching is semantic rather than lexical, an empty result is a legitimate answer meaning the library attests the idea once, and same-chapter neighbors are near-duplicates that 'prove nothing.' That last point prevents a real false-positive pattern an agent would otherwise fall into.

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 short paragraphs ordered by importance: what it does and its sibling boundary first, use cases and the key parameter second, the empty-result caveat last. No sentence restates the name or the schema.

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 return-value burden and does handle the most important cases: that results report their actual language and that zero results is meaningful. It stops short of saying what a result actually contains (citation, work, verse text, similarity measure), which is the one gap for an agent consuming the output.

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 explaining the intent behind exclude_same_work — independent corroboration versus repetition — and warning that the adjacent verse is trivially similar. It does not add anything for limit or verse beyond what the schema already documents.

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 (find passages similar to a given verse) plus the mechanism that defines it: similarity by meaning, not by shared words. It explicitly contrasts itself with the sibling search_texts, so an agent can choose between them without opening either 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 an explicit routing rule — 'Start here when you already have a verse; when you only have words, a question or a term, use search_texts' — naming the alternative and the condition that selects it. It also lists three concrete use cases (verify a teaching, gather parallels, compare treatments of a subject).

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