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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false, destructiveHint=false), so the description's job is the payload shape — and it does this in unusual depth: field-by-field semantics for `grammar`, `interlinear.words`, `segments.is_content`, morphology codes, and the Psalms `superscription_words` edge case. It adds no rate limits, pagination, or error behavior, which keeps it below a 5 for a read tool whose result size could vary.

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 core purpose and the alternative-routing sentence are front-loaded, which is good, but the remainder is a single dense paragraph with heavy parentheticals, em-dashes, and ALL-CAPS emphasis that reads like a field reference manual rather than tool guidance. The final Psalms superscription sentence is a genuine edge case but is buried at the end of a very long block; the content earns its place, the packaging does not.

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 the full burden of explaining return values and does so thoroughly (grammar, interlinear, segments, morphology codes, superscription). For a 3-parameter fixed lookup the only material omission is the input contract — book naming and verse numbering — which is the one thing a caller must get right before any of the described output can be reached.

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 0% and the description never mentions book, chapter, or verse at all. The most error-prone ambiguity — whether `book` accepts "Ps", "Psalms", an abbreviation, or a canonical index, and whether verse numbering follows Hebrew or English convention — is left entirely unresolved despite the description itself raising superscription/verse-1 folding, which is exactly where numbering conventions bite.

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 states a precise verb+resource (list every Strong's number tagged in a verse) and enumerates the payload (lemma, transliteration, gloss, grammar parse, interlinear). An agent can distinguish this from get_verse_text or get_strongs_detail without opening any schema, since the scope is explicitly verse-scoped and word-level.

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?

"Use this when the user asks about original language, word meaning, or grammar, or when you want to do word-level analysis" gives clear triggering conditions, plus two strong exclusions-as-guidance (never parse grammar from memory, never reconstruct word order from memory). It stops short of naming which sibling to use instead (get_strongs_detail for a lemma-level study, get_word_origin for etymology), so overlap with those remains for the agent to infer.

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