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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower, and the description still adds real behavioral context: text is returned verbatim from a stored corpus, KJV is complete while WEB is only partially held and silently falls back to KJV with notification. It does not describe error behaviour for unrecognised references, which is the one notable gap.

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 and well organised: purpose, then usage, then input examples, then the anti-hallucination constraint. The closing sentence ("The Word points to Christ, who is its subject (John 5:39)") is devotional flourish that adds no operational value and is the one piece of text that does not earn its place.

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?

An output schema exists, so return formatting need not be explained, and the description covers corpus provenance, translation behaviour, accepted reference forms and the hallucination guard. Given only two params and full schema coverage, the definition is essentially complete; failure modes for invalid references are the only unaddressed area.

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 100%, so 3 is the baseline, and the description adds legitimate meaning on top: reference accepts reader-style and even topical formulations ("the verse about love being patient"), and the translation field's coverage limits and fallback are restated in human terms. It stops short of clarifying malformed or out-of-range reference handling.

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 names a specific verb and resource ("Read a Bible passage verbatim from a stored text") and states the exact scope (verse, verse range, whole chapter) with worked examples. An agent can distinguish this from siblings like scripture_search or scripture_context 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?

It gives one very strong routing rule, "Never quote Scripture from memory when this tool is available," plus the range of inputs to use it for (verse, range, chapter) and sample user phrasings. What is missing is explicit signposting away from near-neighbours such as scripture_search or verses_for, so the agent must infer the boundary rather than being told it.

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