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

Annotations already cover the read-only, closed-world, non-destructive profile, and the description adds substantive behavior beyond them: results are never truncated, chunk overlap means surrounding verses are often returned, and an oversized range yields a mode: range_too_large payload with a focus prompt. That last detail is exactly the kind of non-obvious response behavior an agent needs before calling.

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 with the core action and scope, then layered with progressively finer operational detail; nearly every sentence carries an actionable constraint. It is dense and slightly over-capitalized in places (ALSO, ASK THE USER), 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?

With no output schema, the description correctly covers the shape of an error-ish return (mode: range_too_large) and the truncation guarantee, which is the crucial part for this tool. It stops short of describing the normal successful return structure or pagination, and leaves book/chapter formatting unaddressed, so it is strong but not exhaustive.

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 only 25% (just verse_end), but the description compensates well by explaining the distinct semantics of verse alone (chunk covering that verse) versus verse_end also (full overlapping-chunk sweep) and the 100-verse cap that the schema states. The remaining gap is `book` and `chapter`, which have no format guidance anywhere — an agent must guess whether "Psalms" or "Psalm 23" style input is expected.

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 (fetch Matthew Henry's commentary) plus scope (a verse or verse range), and explicitly positions itself relative to the sibling get_commentary_section ("Peer of get_commentary_section, not a fallback"). An agent can distinguish it from the other commentary tool 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 explicit when-to-call guidance ("Call it when the question concerns a verse's meaning, theology, or application"), spells out the verse-only vs verse+verse_end distinction, and prescribes the exact recovery behavior for range_too_large (ask the user to narrow rather than calling repeatedly). It also names the alternative tool and rules out treating it as a fallback.

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