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

Annotations already mark the tool read-only and non-destructive, and the description adds substantial behavioral context beyond that: deterministic blank patterns across calls, LCS-based alignment so early word drops don't cascade, KJV italic words and punctuation being excluded from scoring, stripped Psalm titles, the drill-on-miss feedback loop, and next_level gating on clean recall. Nothing in the description contradicts the readOnlyHint.

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 description is long but every paragraph carries operational information needed to invoke the tool correctly, and the purpose and mode split are front-loaded. It loses a point for partial redundancy, since the level-hiding semantics in the description roughly restate the schema's level parameter description.

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?

Given there is no output schema, the description carries the full burden of explaining return values, and it does so for both modes: blanked verse for drills, and accuracy/missed/added/first_divergence for checks. Combined with annotations covering the safety profile, nothing an agent needs to select a mode, set a level, and interpret a response is missing.

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 the baseline is 3, but the description adds genuine meaning beyond the schema: the determinism property for level ('same reference and level always produce the same blanks'), the italic-word scoring rule for attempt, and the Psalm-title stripping for reference. Some level detail is redundant with the schema's own parameter description, but the added nuances elevate it above baseline.

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 first sentence states a specific verb and resource ('Help a member learn a verse by heart') and immediately names the two operating modes, DRILL and CHECK. The function is concrete enough that an agent can distinguish it from siblings like get_verse (plain retrieval) and verify_scripture (text/reference checking) even though no sibling is named.

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?

The description gives explicit mode-selection guidance: 'DRILL (omit `attempt`)' vs 'CHECK (pass `attempt`)', plus explicit don'ts ('must not be quizzed', 'Present this as memory work, not as a test of faith'). It does not, however, name sibling alternatives or state when this tool should NOT be chosen over get_verse or verify_scripture, so it stops short of full when/when-not coverage.

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