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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description correctly spends its words elsewhere and adds a valuable expectation-setting line: it returns sources and gaps rather than an answer, so the agent must weigh them. It says nothing about how many sources come back or how gaps appear, but the presence of an output schema lowers that burden.

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?

The routing instruction and the return-behavior caveat are front-loaded and every clause is functional rather than decorative. The middle enumeration is dense with semicolons and would scan better as a list, but no sentence is filler.

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 14-way multiplexer with full schema coverage, annotations, and an output schema, the description covers most of what an agent needs to choose a kind and supply a query. The missing explanations for the truth and authorship kinds are the one substantive hole, since the schema points back here for that information.

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?

Adds real meaning beyond the schema by mapping each kind to a query format: a reference for text/context/application/word, a Strong's number for lexical lookup, a word or phrase for topic-style kinds, and a verse for reception/tradition/difference. The gap is that the schema's kind field defers entirely to the description, yet 'truth' and 'authorship' are never explained, leaving two enum values opaque.

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?

Specific verb and resource ('gathers the relevant texts in one call') plus an explicit 'Start here' routing signal that separates it from single-passage siblings like get_passage or lookup. The kind enumeration clarifies the scope of the tool, though it omits two enum values (truth, authorship), so the stated scope is slightly narrower than the actual tool.

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?

States the entry condition clearly: broader Bible study or theology questions, and implicitly contrasts with narrower lookups by promising everything in one call. It does not name a specific alternative tool or say when not to use it, so an agent must infer that single-verse lookups belong to get_passage.

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