Conciseness

Largely efficient, table-driven, domain-practitioner guidance ('a wildly large |n| (>4) usually means a bad fit', 'r² ≥0.95 good; <0.90 → inspect') rather than padding. It sits between the 5 and 3 anchors: the Step 3 'Meaning' column restates concepts Claude already knows ('Concentration giving half-maximal effect — the potency', 'Lower = more potent'), so not every token earns its place — matching the 4 anchor (efficient, minor over-explanation that could be trimmed).

Actionability

Fully executable: a copy-paste-ready 'tu run DoseResponse_calculate_ic50' command with a realistic JSON payload, the exact return fields ('ic50, ic50_95_confidence_interval, hill_slope, emax, emin, r_squared, log_ic50'), named alternative tools with their exact parameter names ('DoseResponse_compare_potency with conc_a/resp_a/conc_b/resp_b'), and a real fallback script ('scripts/fit_dose_response.py'). The common case is covered by a complete example, matching the 5 anchor.

Workflow Clarity

A clear 4-step sequence (prepare data → fit → interpret → quality gotchas) with explicit validation checkpoints and error-recovery feedback: 'you need ≥4 points… ideally 6–8 spanning both plateaus', r² thresholds gating trust in the IC50, and recovery actions when checks fail ('Report the IC50 as approximate… and recommend wider concentrations', 'flag it rather than forcing one IC50', fold-shift only meaningful 'if both fits are good (r²≥0.95)'). This matches the 5 anchor (explicit validation steps with feedback loops), and the operation is read-only analysis so no destructive-operation cap applies.

Progressive Disclosure

Good structure: well-organized sections, and the advanced path is properly deferred one level deep to an existing bundle file ('scripts/fit_dose_response.py runs a scipy 4PL fit from a CSV'), which is real and clearly signaled. It falls short of the 5 anchor because the full interpretation guide (Step 3 meanings, Step 4 gotchas) is inlined in a ~78-line body with no separate reference material, so content is well-placed but not split across files.

Specificity

The description lists multiple concrete actions — 'IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency from paired concentration vs response data' and 'Fits the 4-parameter logistic (Hill sigmoidal) model' — giving comprehensive, specific coverage that would anchor at 5. However, the trigger clause uses second person ('Use when you have concentrations + responses and need a potency value'), which the judging guidelines penalize by reducing the specificity score by 1.

Completeness

Both 'what' and 'when' are explicit with concrete trigger phrases: the what ('Dose-response / concentration-response curve fitting — IC50, EC50, Hill slope, Emax/Emin efficacy, and relative potency… Fits the 4-parameter logistic') and the when ('Use when you have concentrations + responses and need a potency value, to compare two compounds' potency, or to judge curve quality'). It also adds negative boundaries, exceeding the 5 anchor.

Trigger Term Quality

Natural keyword coverage is comprehensive, including synonyms and variations users would actually say: 'dose-response / concentration-response', 'IC50', 'EC50', 'potency', 'curve fitting', 'drug screening', 'enzyme/cell assays', 'agonist/antagonist pharmacology'. It matches the 5 anchor (comprehensive natural terms including synonyms) and is not merely technical jargon.

Distinctiveness Conflict Risk

A clear niche (paired concentration-vs-response curve fitting) with distinct triggers, plus explicit NOT-for routing to sibling skills ('NOT for image-derived dose-response (use tooluniverse-image-analysis) and NOT for survival/regression (use tooluniverse-statistical-modeling)') minimizes conflict risk — matching the 5 anchor for a clear niche with minimal overlap.